Device intelligent management method and device, computer device and medium

Abstract

The application provides a device intelligent management method and device, computer equipment and medium. The method comprises the following steps: collecting first historical running data of each device in a plurality of devices; monitoring real-time energy consumption of each device; in the case that it is determined that the real-time energy consumption does not meet the energy consumption standard, acquiring second historical running data of an abnormal device; analyzing the second historical running data by using a causal inference algorithm, determining a causal effect value of the real-time energy consumption by quantifying each cause variable, and determining a reason why the real-time energy consumption does not meet the energy consumption standard based on the causal effect value; according to the reason, querying a device operation and maintenance knowledge base to obtain a corresponding energy-saving operation strategy; based on the energy consumption standard and the first historical running data, predicting an energy efficiency evaluation result of each device by using a prediction model; setting a scheduling priority factor of each device according to the energy efficiency evaluation result; and adjusting a production scheduling plan according to the scheduling priority factor and the energy-saving operation strategy. The application can improve the energy efficiency of the device.

Description

Technical Field

[0001] This application relates to the field of intelligent manufacturing technology, and in particular to an intelligent equipment management method, device, computer equipment and medium. Background Technology

[0002] Traditional energy management solutions for Computer Numerical Control (CNC) equipment often rely on server-based monitoring based on fixed thresholds or semi-automatic analysis based on human experience. These solutions suffer from problems such as inaccurate static energy consumption benchmarks, lack of interpretable diagnostics for anomalies, and single-variable predictive models that are disconnected from production scheduling systems. This results in lagging, inaccurate, and difficult-to-close-loop energy efficiency optimization. Summary of the Invention

[0003] This application discloses an intelligent equipment management method, device, computer equipment, and medium, which solves the technical problems in the prior art where energy consumption management relies on static thresholds and human experience, cannot adapt to dynamic changes in equipment, and production scheduling is disconnected from energy efficiency.

[0004] In a first aspect, embodiments of this application provide an intelligent equipment management method, comprising: pre-storing an equipment operation and maintenance knowledge base and preset energy consumption standards; collecting first historical operating data for each of multiple devices; monitoring the real-time energy consumption of each of the multiple devices and comparing it with the energy consumption standards; if it is determined that the real-time energy consumption does not meet the energy consumption standards, obtaining second historical operating data of the abnormal device within a preset historical period; analyzing the second historical operating data using a causal inference algorithm, determining the causal effect value of the real-time energy consumption by quantifying each causal variable, and determining the reason why the real-time energy consumption does not meet the energy consumption standards based on the causal effect value; querying the pre-storing equipment operation and maintenance knowledge base according to the reason why the energy consumption does not meet the energy consumption standards to obtain corresponding energy-saving operation strategies; predicting the energy efficiency assessment results of each device in a future preset time window using a prediction model based on the energy consumption standards and the first historical operating data; setting a scheduling priority factor for each device according to the energy efficiency assessment results; and adjusting the production scheduling plan according to the scheduling priority factor and the energy-saving operation strategies.

[0005] In some embodiments of this application, the step of analyzing the second historical operating data using a causal inference algorithm, determining the causal effect value of the real-time energy consumption by quantifying each causal variable, and determining the reasons why the real-time energy consumption does not meet the energy consumption standard based on the causal effect value includes: preprocessing the second historical operating data to obtain a variable set for causal analysis; performing conditional independence tests on the variables in the variable set to screen potential causal links between variables; performing confounding factor control tests on the causal links to obtain a set of effective causal links; constructing a causal graph based on the set of effective causal links, and using regression analysis to quantify each causal variable to determine the causal effect value of the real-time energy consumption; and sorting the real-time energy consumption according to the magnitude of the causal effect value to determine the reasons why the real-time energy consumption deviates from the energy consumption standard.

[0006] In some embodiments of this application, the step of using regression analysis to quantify the causal effect value of each causal variable on the energy consumption outcome variable includes: for each valid causal link in the set of valid causal links, constructing and solving a regression model with the energy consumption variable as the dependent variable and the corresponding causal variable and other control variables determined according to the causal graph as independent variables, and determining the regression coefficient of the causal variable as the causal effect value.

[0007] In some embodiments of this application, the step of predicting the energy efficiency assessment result of the device in a future preset time window using a prediction model includes: acquiring real-time energy consumption data, processing status data, tool status data, and device alarm data of the device; performing clustering processing on the device alarm data to obtain corresponding energy consumption influence factors; inputting the energy consumption influence factors, the real-time energy consumption data, the processing status data, and the tool status data into a pre-trained multivariate time series prediction model; and acquiring the energy efficiency assessment result of the device in a future preset time window output by the multivariate time series prediction model.

[0008] In some embodiments of this application, after collecting the first historical operating data of each of the multiple devices, the device intelligent management method further includes: obtaining the energy consumption standard of each device under the current production conditions based on the first historical operating data.

[0009] In some embodiments of this application, obtaining the energy consumption standard of each device under the current production conditions based on the first historical operating data includes: cleaning the first historical operating data to obtain cleaned first historical operating data; and determining the energy consumption standard based on the median of the cleaned first historical operating data.

[0010] In some embodiments of this application, the intelligent equipment management method further includes: periodically calculating the energy consumption standard of each device under the same production conditions to obtain historical energy consumption standards; and updating the energy consumption standard of each device under the current production conditions based on the minimum value among the historical energy consumption standards.

[0011] Secondly, this application provides an intelligent equipment management device, comprising: a setting module for pre-storing an equipment operation and maintenance knowledge base and preset energy consumption standards; a monitoring module for collecting first historical operating data of each of a plurality of devices; the monitoring module is further configured to monitor the real-time energy consumption of each of the plurality of devices and compare it with the energy consumption standards; an acquisition module for acquiring second historical operating data of abnormal devices within a preset historical period when it is determined that the real-time energy consumption does not meet the energy consumption standards; and a processing module for analyzing the second historical operating data using a causal inference algorithm, determining the causal effect value of the real-time energy consumption by quantifying each causal variable, and based on the causal effect... The processing module analyzes the historical operating data to determine the cause of the real-time energy consumption not meeting the energy consumption standard using a causal inference algorithm. The processing module is further configured to query the pre-stored equipment operation and maintenance knowledge base to obtain corresponding energy-saving operation strategies based on the cause of the non-compliance with the energy consumption standard. The processing module is also configured to predict the energy efficiency assessment result of each device in a future preset time window using a prediction model based on the energy consumption standard and the first historical operating data. The setting module is further configured to set the scheduling priority factor for each device based on the energy efficiency assessment result. Finally, the processing module is further configured to adjust the production scheduling plan based on the scheduling priority factor and the energy-saving operation strategy.

[0012] Thirdly, this application provides a computer device, which includes a processor and a memory, wherein the processor executes a computer program stored in the memory to implement the device intelligent management method described above.

[0013] Fourthly, this application provides a computer-readable storage medium storing at least one instruction that, when executed by a processor, implements the device intelligent management method described above.

[0014] The intelligent equipment management method provided in this application monitors the real-time energy consumption of equipment. When real-time energy consumption fails to meet standards, a causal inference algorithm is used to accurately pinpoint the cause of this failure. Based on the cause, a corresponding energy-saving operation strategy is determined, and the production schedule is adjusted according to this strategy and scheduling priority factors. This can reduce overall production energy consumption, improve equipment energy efficiency, and achieve energy savings. Attached Figure Description

[0015] Figure 1 This is an application environment diagram of the intelligent device management method provided in the embodiments of this application.

[0016] Figure 2 This is a flowchart of an embodiment of the intelligent device management method provided in this application.

[0017] Figure 3 This is a flowchart of a device intelligent management method provided in another embodiment of this application.

[0018] Figure 4 This is a schematic diagram of the intelligent device management apparatus provided in the embodiments of this application.

[0019] Figure 5 This is a structural diagram of the computer device provided in the embodiments of this application. Detailed Implementation

[0020] For ease of understanding, some concepts related to the embodiments of this application are illustrated and explained by way of example for reference.

[0021] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.

[0022] In traditional manufacturing equipment energy management, especially for high-value, high-energy-consuming equipment like CNC machine tools, a linear management process based on manual experience is typically employed. The specific operational method is as follows: First, managers determine a fixed percentage (e.g., 80% of the rated power) based on the rated power indicated on the equipment's nameplate as a fixed threshold for judging whether the equipment is consuming too much energy. This threshold is then fine-tuned based on experience, serving as the energy consumption standard. Second, in daily energy optimization, the process relies heavily on the senses and experience of maintenance workers. For example, they listen for unusual noises during equipment operation to determine if there are any abnormal energy consumption issues and modify the equipment's control parameters based on experience to attempt to reduce energy consumption.

[0023] While this existing approach has the advantage of being simple to operate (requiring only a lookup of the rated parameter table), its technical shortcomings are also significant. First, the rated power of the equipment is merely a theoretical maximum or nominal value, which deviates greatly from the actual energy consumption under real-world operating conditions. Using this as a benchmark cannot accurately reflect the equipment's true energy consumption level. Second, fine-tuning thresholds based on human experience lacks scientific basis and data support, resulting in inaccurate energy consumption standards. Third, as equipment is used and ages, its performance gradually deteriorates. Relying on manual listening for judgment cannot systematically adapt to the changes in energy consumption characteristics caused by equipment deterioration, leading to poor energy consumption optimization and delayed response. From a value assessment perspective, this reliance on human experience results in low management efficiency, long fault diagnosis and troubleshooting cycles, and an inability to provide effective data support for production scheduling, increasing the company's operating costs and management complexity.

[0024] Based on the aforementioned technical issues, this application determines the cause of the non-compliance of real-time energy consumption with energy consumption standards by monitoring the real-time energy consumption of the equipment. Then, it uses a causal inference algorithm to accurately locate the cause of the non-compliance and determines the corresponding energy-saving operation strategy based on the cause. The production schedule is then adjusted according to the energy-saving operation strategy and the scheduling priority factor, which can reduce the overall production energy consumption, improve the energy efficiency of the equipment, and achieve the effect of energy saving.

[0025] To better understand the intelligent device management method provided in the embodiments of this application, the application scenarios of the intelligent device management method of this application are described below.

[0026] Figure 1 This is a schematic diagram illustrating the implementation environment of the intelligent device management method provided in this application embodiment. For example... Figure 1 As shown, in some embodiments of this application, the intelligent device management method can be applied to a computer device 1 (e.g., a server), which can communicate with multiple devices 2. Devices 2 can be CNC machines, CNC machine tools (such as milling machines, lathes, grinding machines, punching machines, drilling machines, boring machines, gear machines, etc.), CNC electrical discharge machining tools, CNC laser cutting machines, CNC plasma cutting machines, injection molding machines, die-casting machines, industrial robots, etc.

[0027] In this embodiment, the computer device 1 can be an edge computing gateway deployed at the production site, a remote server located in a data center, or a cloud computing platform providing cloud services. The computer device 1 receives operational data uploaded by the device 2 through a wired or wireless communication link established with the device 2, and processes and analyzes the data to achieve intelligent management of the device.

[0028] The technical solutions of this application will be described in detail below with specific embodiments. The specific embodiments described below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0029] Figure 2 This is a flowchart illustrating the intelligent device management method provided in this embodiment. The method in this embodiment can be executed by a computer device, such as... Figure 2 As shown, the method in this embodiment may include: Step S101: Pre-store the equipment operation and maintenance knowledge base and preset the energy consumption standard.

[0030] In this embodiment, an equipment operation and maintenance knowledge base and preset energy consumption standards can be pre-stored in the computer device. The equipment operation and maintenance knowledge base is a structured database that stores the mapping relationship between the causes of equipment failures and corresponding solutions or operational suggestions. The equipment operation and maintenance knowledge base can be formed by digitizing and storing the experience and knowledge of domain experts. The preset energy consumption standards are used to compare with real-time energy consumption to accurately determine whether the device is currently in a high-energy-consumption or abnormal-energy-consumption state.

[0031] Step S102: Collect the first historical operating data of each of the multiple devices.

[0032] In this embodiment, the first historical operating data includes the real-time power, cumulative energy consumption, start / stop status, running time, and corresponding production condition identifiers of the equipment within a preset historical time period. The computer equipment collects the first historical operating data from each device according to a preset sampling frequency (e.g., every 1 minute or every 5 minutes).

[0033] Step S103: Monitor the real-time energy consumption of each of the multiple devices and compare it with the energy consumption standard.

[0034] In this embodiment, real-time energy consumption is a key indicator reflecting the current energy efficiency level of the equipment. By monitoring the equipment's energy consumption in real time, abnormal fluctuations in energy consumption during equipment operation can be detected in a timely manner, providing a data foundation for subsequent energy efficiency optimization, fault warning, and intelligent production scheduling. The computer equipment can acquire real-time energy consumption data from each device according to a preset sampling frequency (e.g., once per second or once per minute).

[0035] Real-time energy consumption refers to the data representing the electrical energy or power consumed by equipment during operation. This data is a core indicator for determining whether equipment is operating efficiently. Real-time energy consumption can be obtained through high-frequency data collection using smart meters or power sensors installed on the equipment. For example, in a CNC machining workshop, a smart meter can be deployed on each CNC machine tool to collect the equipment's instantaneous power and cumulative power consumption data once per second. The smart meter communicates with a computer, sending the collected instantaneous power and cumulative power consumption data to the computer. The computer can clean and timestamp the received data. By comparing the real-time energy consumption with energy consumption standards, the energy consumption of each piece of equipment can be determined.

[0036] In some embodiments, the computer equipment can monitor multiple similar or different types of equipment in a production workshop, production line, or factory area. For example, the computer equipment can simultaneously monitor the real-time power of 50 CNC machine tools of different models in a CNC workshop and display the data visually on the monitoring interface in the form of a dashboard or graph.

[0037] Step S104: If it is determined that the real-time energy consumption does not meet the energy consumption standard, the second historical operating data of the abnormal device within a preset historical period is obtained.

[0038] In this embodiment, to accurately pinpoint the root cause of abnormal energy consumption, it is not sufficient to rely solely on single energy consumption data; a comprehensive analysis combining multi-dimensional operational data of the equipment prior to the anomaly is also necessary. Therefore, when the computer determines that real-time energy consumption does not meet the preset energy consumption standard, it automatically triggers a second historical operational data backtracking mechanism for the abnormal equipment. This mechanism extracts operational data from a period prior to the anomaly, providing complete data support for subsequent anomaly diagnosis and process optimization.

[0039] The energy consumption standard can be determined based on the equipment's second historical operating data. For example, the energy consumption standard can be determined based on the energy consumption data of the equipment under normal processing conditions. For instance, for a specific model of CNC machine tool processing a specific workpiece, the energy consumption standard for a single product can be determined to be 1.2 kWh. When the actual energy consumption of the equipment processing a single product is monitored to reach 1.5 kWh, it is determined that the real-time energy consumption does not meet the energy consumption standard.

[0040] In some embodiments, the preset historical time period can be several hours or several days prior to the time point when the energy consumption anomaly is determined. For example, if the system determines that the device's energy consumption exceeds the standard at 14:00 in the afternoon, it will automatically obtain all the second historical operating data of the device from 10:00 in the morning to 14:00 as the analysis sample.

[0041] The second set of historical operating data includes, but is not limited to, the equipment's operating status, process parameters, environmental data, and alarm information. For example, for a CNC machine tool, the acquired operating data may include spindle speed, spindle load, feed rate, current of each servo axis, spindle temperature, coolant temperature, tool number, name of the currently executed machining program, and all alarm codes generated during this period.

[0042] In this embodiment, when real-time energy consumption is detected to be inconsistent with energy consumption standards, the computer device acquires second historical operating data of the device within a preset historical period to accurately define the data range for subsequent root cause analysis. For example, in a CNC machining unit, the computer device detects an abnormal rise in the power curve of a CNC engraving machine during the machining of a mobile phone frame, triggers an alarm, and automatically acquires energy-related operating data of the device from the tool change time to the alarm trigger time, rather than performing a full analysis of all historical data of the device, thereby improving the targeting and efficiency of the analysis.

[0043] Step S105: The second historical operating data is analyzed using a causal inference algorithm. The causal effect value of real-time energy consumption is determined by quantifying each causal variable. Based on the causal effect value, the reasons why the real-time energy consumption does not meet the energy consumption standard are determined.

[0044] In this embodiment of the application, in order to accurately identify the key factors causing abnormal energy consumption from the acquired second historical operating data and avoid drawing misleading conclusions based solely on correlation, a causal inference algorithm is used to analyze the operating data to reveal the intrinsic driving mechanism between variables and achieve reliable location of the root cause.

[0045] One approach is to employ a causal inference algorithm to uncover the intrinsic driving relationships between variables within the second set of historical operational data. This algorithm uses multiple variables from the second set of historical operational data as candidate causal variables and calculates the causal effect value of each causal variable on the energy consumption outcome variable through statistical tests and model fitting. Causal variables are the potential factors in the operational data that may influence the energy consumption outcome. The causal effect value is a quantitative indicator used to characterize the degree to which a change in a particular causal variable affects the change in the energy consumption outcome variable, while keeping other variables constant.

[0046] In some embodiments, the causal inference algorithm includes the Peter and Clark Momentary Conditional Independence (PCMCI) algorithm. This algorithm aims to automatically and data-drivenly discover direct causal relationships and their time lags between variables in high-dimensional time series data, without prior knowledge. For example, by inputting dozens of time series variables such as spindle temperature, current, and vibration into the PCMCI algorithm, the algorithm will output a causal network diagram showing how these variables interact and ultimately affect energy consumption.

[0047] In some embodiments, the causal effect value is obtained by constructing and solving a regression model for each valid causal link based on the constructed causal graph. For example, for the causal link of "spindle temperature (first 5 minutes) and real-time energy consumption", the causal effect value is calculated to be 0.62 through regression analysis. This means that after controlling for other factors, for every 1 unit increase in spindle temperature, the equipment energy consumption increases by an average of 0.62 units.

[0048] In some embodiments, determining the reasons why real-time energy consumption does not meet energy consumption standards includes: sorting the variables according to the magnitude of their causal effect values, and determining the variables and their causal effect values ​​that meet preset conditions in the sorting results as the cause output. Specifically, a causal inference algorithm is used to analyze the second historical operating data, and the causal effect values ​​of real-time energy consumption are determined by quantifying each causal variable. Determining the reasons why real-time energy consumption does not meet energy consumption standards based on causal effect values ​​includes: preprocessing the second historical operating data to obtain a variable set for causal analysis; performing conditional independence tests on the variables in the variable set to screen potential causal links between variables; performing confounding factor control tests on the causal links to obtain a set of effective causal links; constructing a causal graph based on the set of effective causal links, and using regression analysis to quantify each causal variable to determine the causal effect value of real-time energy consumption; and sorting the variables according to the magnitude of the causal effect values ​​to determine the reasons why real-time energy consumption deviates from energy consumption standards. The method of using regression analysis to quantify each causal variable in order to determine the causal effect value of real-time energy consumption includes: for each effective causal link in the effective causal link set, with the energy consumption variable as the dependent variable and the corresponding causal variable and other control variables determined according to the causal diagram as independent variables, constructing and solving a regression model, and determining the regression coefficient of the causal variable as the causal effect value.

[0049] For example, in a CNC machine tool machining scenario, to determine the cause of abnormal real-time energy consumption, the computer can acquire the machine's operating data for the four hours prior to the alarm trigger and preprocess this historical operating data, including data cleaning, timestamp alignment, and removal of idle data segments caused by machine standby or tool changing. This yields a variable set for causal analysis. This variable set includes multiple time-series variables such as spindle temperature, spindle load, feed rate, coolant temperature, vibration amplitude, and real-time energy consumption. The computer performs conditional independence tests based on this variable set to screen for potential causal links between variables. For example, through the PC phase of the PCMCI algorithm, the algorithm performs conditional independence tests on any two variables in the variable set, initially identifying multiple potential causal links such as spindle temperature and real-time energy consumption, spindle load and real-time energy consumption, feed rate and real-time energy consumption, coolant temperature and spindle temperature, and vibration amplitude and spindle load. The computer performs confusion factor control tests on these potential causal links. For example, it executes the MCI phase of the PCMCI algorithm. By re-examining the parent variables of the causal and outcome variables in each potential causal link as a condition set, spurious links caused by confounding factors or intermediate variables are eliminated. For example, MCI testing revealed that the potential link "coolant temperature and real-time energy consumption" was no longer significant after controlling for spindle temperature, thus identifying it as a spurious link and eliminating it. This yields a set of valid causal links containing relationships such as "spindle temperature and real-time energy consumption," "spindle load and real-time energy consumption," "feed rate and real-time energy consumption," and "vibration amplitude and spindle load." Based on this set of valid causal links, the computer device constructs a directed acyclic causal graph, which visually illustrates the causal transmission paths between variables.

[0050] The computer equipment employs regression analysis to quantify various causal variables and determine the causal effect value of real-time energy consumption. Specifically, for each valid causal link pointing to real-time energy consumption in the causal graph, real-time energy consumption is used as the dependent variable, and the corresponding causal variable and other parent variables of the causal variable determined according to the causal graph are used as independent variables. A linear regression model is constructed and solved, and the regression coefficient of the causal variable is determined as the causal effect value. For example, for the link "spindle temperature and real-time energy consumption," the independent variables in the regression model include spindle temperature and the parent variable of spindle temperature (such as ambient temperature) determined according to the causal graph. The causal effect value of spindle temperature is calculated to be 0.62. Similarly, the causal effect value of spindle load is 0.48, and the causal effect value of feed rate is 0.31. The computer equipment sorts these causal effect values ​​according to their magnitude and determines that the abnormal increase in spindle temperature is the main reason for the deviation of real-time energy consumption from the energy consumption standard.

[0051] Step S106: Based on the reasons for not meeting energy consumption standards, query the pre-stored equipment operation and maintenance knowledge base to obtain the corresponding energy-saving operation strategy.

[0052] In this embodiment, the computer device performs a matching query in a pre-stored equipment operation and maintenance knowledge base based on the reason for non-compliance with energy consumption standards to obtain the corresponding energy-saving operation strategy. The equipment operation and maintenance knowledge base is a structured database that stores the mapping relationship between equipment failure causes and corresponding solutions or operational suggestions. The energy-saving operation strategy is a specific and actionable guiding suggestion generated for a specific cause of abnormal energy consumption.

[0053] In some embodiments, the equipment operation and maintenance knowledge base may be formed by digitizing and storing the experience and knowledge of domain experts. For example, the knowledge base maintains a rule: if the cause is spindle overheating, the corresponding operating strategy includes: 1. Checking whether the spindle cooling circulation system is working properly; 2. Checking whether the spindle bearing lubrication is good; 3. Appropriately reducing the spindle speed or feed rate.

[0054] In some embodiments, energy-saving operation strategies can be pushed to field operators or equipment maintenance personnel through a human-machine interface. For example, a notification window may pop up on the terminal screen next to the equipment, displaying: "The increased energy consumption has been diagnosed as being mainly caused by spindle overheating. It is recommended to check the spindle cooling system first. For specific operation instructions, please click [View Details]".

[0055] Step S107: Based on energy consumption standards and first historical operating data, use a prediction model to predict the energy efficiency assessment results of each device in a future preset time window.

[0056] In this embodiment, to avoid production interruptions or resource waste caused by passively responding to abnormal energy consumption, the computer equipment uses a pre-trained predictive model based on energy consumption standards and the first historical operating data of all equipment to predict the energy efficiency performance of multiple devices within a preset future time window. The predictive model is a computational model trained on historical data capable of extrapolating future trends. The preset future time window can be a future period of time for which the prediction is made. The energy efficiency assessment result is a predicted value or rating of the equipment's energy utilization efficiency within the future period.

[0057] In some embodiments, the prediction model includes a multivariate time series prediction model, specifically a regression model within the Skforecast model framework. This model can integrate multiple feature variables to predict a target time series. For example, a model can be constructed with the average energy consumption per unit of each CNC machine over the next three days as the prediction target. The data input to the prediction model can include historical energy consumption data, machining status data, tool status data, and equipment alarm data. For instance, the average daily energy consumption per unit over the past 30 days, the cumulative daily spindle running time (machining status), the number of workpieces processed by the current tool (tool status), and the types and frequency of alarms occurring daily (alarm data) can be organized into a feature vector and input into the model. This yields the energy efficiency assessment results for the equipment within a preset future time window.

[0058] In some embodiments, the energy efficiency assessment result can be a specific value of the predicted future energy consumption per unit of product, or a level based on that value. For example, if the model predicts that the average energy consumption per unit of device A over the next three days will be 1.1 kWh, which is lower than the energy consumption standard of 1.2 kWh, then the energy efficiency assessment result for the device is "high efficiency"; if the predicted result is 1.4 kWh, then the assessment result is "inefficient".

[0059] Step S108: Set the scheduling priority factor for each device based on the energy efficiency assessment results.

[0060] In this embodiment, to quantify the predicted future energy efficiency status of multiple devices into decision parameters that can be directly used by the production scheduling system, and to achieve energy efficiency-oriented differentiated scheduling, thereby intelligently managing each device, the computer device sets a corresponding scheduling priority factor for each device according to a preset mapping rule based on the energy efficiency assessment results of each device. The scheduling priority factor is a weighted coefficient or level identifier used to quantify the degree to which a device should be given priority in production scheduling.

[0061] In some embodiments, there is a preset mapping relationship between energy efficiency assessment results and scheduling priority factors. For example, for devices with an energy efficiency assessment result of "high efficiency", the scheduling priority factor is set to "high" or the value "1"; for devices with an assessment result of "good", the priority factor is "medium" or the value "2"; and for devices with an assessment result of "inefficient", the priority factor is "low" or the value "3".

[0062] In some embodiments, the process of setting scheduling priority factors is dynamic and periodic. For example, the system refreshes the list of scheduling priority factors for all devices every hour or after each batch of tasks is completed, based on the latest forecast results. Scheduling priority factors can be written to a shared data table accessible by a production scheduling system. For instance, the system writes device numbers and their corresponding priority factors to a designated table in the manufacturing execution system database for use by advanced planning and scheduling systems.

[0063] Step S109: Adjust the production scheduling plan according to the scheduling priority factor and energy-saving operation strategy.

[0064] In this embodiment, the computer equipment adjusts the current production schedule based on scheduling priority factors and energy-saving operation strategies. Specifically, on the one hand, based on the scheduling priority factors, production tasks are preferentially allocated to equipment with higher energy efficiency assessment results, while equipment with lower energy efficiency assessment results is designated as standby or performs non-urgent tasks. On the other hand, for equipment with energy-saving operation strategy guidelines, corresponding maintenance time windows are reserved in the production schedule, or tasks involving that equipment are adjusted to a period after maintenance operations are performed, to ensure that the equipment can resume production load only after it has recovered to a high-efficiency state. Through the above adjustments, optimal energy efficiency of the entire production line or workshop is achieved while meeting production task requirements.

[0065] Through the above steps, the intelligent equipment management method provided in this application monitors the real-time energy consumption of equipment. When real-time energy consumption fails to meet standards, a causal inference algorithm is used to accurately pinpoint the cause of this failure. Based on the cause, a corresponding energy-saving operation strategy is determined, and production scheduling is adjusted according to this strategy and scheduling priority factors. This transforms manual, experience-driven fault diagnosis into data-driven automated root cause analysis, significantly improving diagnostic efficiency and accuracy, thereby enhancing the human-machine interaction experience. Furthermore, by predicting the future energy efficiency status of equipment and dynamically adjusting scheduling priorities, a deep integration of production resources and energy consumption management is achieved, enriching the strategic dimensions of production management. The intelligent equipment management method provided in this application solves the technical problems of existing technologies where energy consumption management relies on static thresholds and manual experience, cannot adapt to dynamic equipment changes, and is disconnected from scheduling and energy efficiency. It achieves the technical effects of reducing overall production energy consumption, improving equipment energy efficiency, and realizing energy conservation.

[0066] Figure 3 This is a flowchart illustrating a device intelligent management method according to another embodiment of this application. The method in this embodiment can be executed by a computer device, such as... Figure 3 As shown, the method in this embodiment may include: Step S301: Pre-store the equipment operation and maintenance knowledge base and preset the energy consumption standard.

[0067] Step S302: Collect the first historical operating data of each of the multiple devices.

[0068] The specific implementation methods of steps S301-S302 are as follows: Figure 2 The steps S101-S102 are the same and will not be repeated here.

[0069] Step S303: Obtain the energy consumption standard of each device under the current production conditions based on the first historical operating data.

[0070] In this embodiment, to eliminate the interference of abnormal operating conditions and peak data during start-up and shutdown on the energy consumption benchmark calculation, it is necessary to first clean the collected first historical operating data, removing equipment downtime, start-up / shutdown transition periods, and noise data that significantly exceeds reasonable threshold ranges, thereby obtaining cleaned historical operating data. Based on the cleaned first historical operating data, the energy consumption distribution of each device under specific production conditions can be statistically analyzed, and the median of this distribution can be selected as the initial energy consumption standard for each device under the current production conditions. Using the median instead of the average as the energy consumption standard can effectively avoid the drift effect of individual extreme load periods on the benchmark value, making the energy consumption standard more robust.

[0071] Specifically, the energy consumption standard for each device under the current production conditions is determined based on the first historical operating data, including: cleaning the first historical operating data to obtain cleaned first historical operating data; and determining the energy consumption standard based on the median of the cleaned first historical operating data. For example, for a certain injection molding machine under "medium load" conditions, the cleaned effective unit product energy consumption data for the past week are as follows: 1.2 kWh, 1.25 kWh, 1.15 kWh, 1.3 kWh, 2.5 kWh (abnormalities removed), and 1.18 kWh. After sorting, the median is taken to determine the energy consumption standard for this operating condition as 1.2 kWh.

[0072] In this embodiment, to ensure that energy consumption standards continuously approach their optimal operating range as equipment ages and processes are optimized, thus preventing the energy efficiency benchmark of the equipment from deteriorating year by year, the intelligent equipment management method provided in this application further includes: periodically calculating the energy consumption standards of each device under the same production conditions to obtain historical energy consumption standards; and updating the energy consumption standards of the device under the current production conditions based on the minimum value in the historical energy consumption standards. For example, assuming that the median of the historical energy consumption standards calculated for the above-mentioned injection molding machine in four consecutive statistical periods are 1.2 kWh, 1.15 kWh, 1.18 kWh, and 1.10 kWh, the computer device will automatically extract the minimum value of 1.10 kWh as the currently effective updated energy consumption standard. This standard update mechanism driven by historical optimal values ​​can continuously compress the space for ineffective energy consumption and guide equipment management strategies toward historically optimal energy efficiency levels. Step S304: Monitor the real-time energy consumption of each of the multiple devices and compare it with the energy consumption standards.

[0073] Step S304: Monitor the real-time energy consumption of each of the multiple devices and compare it with energy consumption standards.

[0074] Step S305: If it is determined that the real-time energy consumption does not meet the energy consumption standard, the second historical operating data of the abnormal device within a preset historical period is obtained.

[0075] Step S306: The second historical operating data is analyzed using a causal inference algorithm. The causal effect value of real-time energy consumption is determined by quantifying each causal variable. Based on the causal effect value, the reasons why the real-time energy consumption does not meet the energy consumption standard are determined.

[0076] Step S307: Based on the reason for not meeting the energy consumption standard, query the pre-stored equipment operation and maintenance knowledge base to obtain the corresponding energy-saving operation strategy.

[0077] Step S308: Based on the energy consumption standard and the first historical operating data, use a prediction model to predict the energy efficiency assessment results of each device in a future preset time window.

[0078] Step S309: Set the scheduling priority factor for each device based on the energy efficiency assessment result.

[0079] Step S310: Adjust the production scheduling plan according to the scheduling priority factor and the energy-saving operation strategy.

[0080] The specific implementation methods of steps S304-S310 are as follows: Figure 2 Steps S103-S108 are the same and will not be repeated here.

[0081] Figure 4This is a functional block diagram of the intelligent device management apparatus provided in this application embodiment. The intelligent device management apparatus 40 operates on computer device 1. The intelligent device management apparatus 40 includes a setting module 401, a monitoring module 402, an acquisition module 403, and a processing module 404. The module / unit referred to in this application refers to a series of computer-readable instruction segments that can be acquired by a processor and perform a fixed function, and which are stored in a storage device.

[0082] The setting module 401 is used to pre-store the equipment operation and maintenance knowledge base and preset energy consumption standards; the monitoring module 402 is used to collect the first historical operation data of each of the multiple devices; the monitoring module 402 is also used to monitor the real-time energy consumption of each of the multiple devices and compare it with the energy consumption standards; the acquisition module 403 is used to acquire the second historical operation data of the abnormal device within a preset historical period when it is determined that the real-time energy consumption does not meet the energy consumption standards; the processing module 404 is used to analyze the second historical operation data using a causal inference algorithm, determine the causal effect value of the real-time energy consumption by quantifying each causal variable, and determine the real-time energy consumption based on the causal effect value. The causal inference algorithm for reasons for non-compliance with energy consumption standards analyzes the historical operating data; the processing module 404 is also used to query the pre-stored equipment operation and maintenance knowledge base according to the reasons for non-compliance with energy consumption standards to obtain the corresponding energy-saving operation strategy; the processing module 404 is also used to predict the energy efficiency assessment result of each device in a future preset time window based on the energy consumption standards and the first historical operating data using a prediction model; and the setting module 401 is used to set the scheduling priority factor of each device according to the energy efficiency assessment result; the processing module 404 is also used to adjust the production scheduling plan according to the scheduling priority factor and the energy-saving operation strategy.

[0083] In some embodiments of this application, the processing module 404 is further configured to preprocess the second historical operating data to obtain a variable set for causal analysis; perform conditional independence tests on the variables in the variable set to screen potential causal links between variables; perform confounding factor control tests on the causal links to obtain a set of effective causal links; construct a causal graph based on the set of effective causal links, and use regression analysis to quantify each causal variable to determine the causal effect value of the real-time energy consumption; and determine the reasons for the deviation of the real-time energy consumption from the energy consumption standard by sorting the causal effect values.

[0084] In some embodiments of this application, the processing module 404 is further configured to construct and solve a regression model for each valid causal link in the set of valid causal links, with the energy consumption variable as the dependent variable and the corresponding causal variable and other control variables determined according to the causal graph as independent variables, and determine the regression coefficient of the causal variable as the causal effect value.

[0085] In some embodiments of this application, the processing module 404 is further configured to acquire real-time energy consumption data, processing status data, tool status data, and equipment alarm data of the device; perform clustering processing on the equipment alarm data to obtain corresponding energy consumption impact factors; input the energy consumption impact factors, the real-time energy consumption data, the processing status data, and the tool status data into a pre-trained multivariate time series prediction model; and acquire the energy efficiency evaluation results of the device in a future preset time window output by the multivariate time series prediction model.

[0086] In some embodiments of this application, the acquisition module 403 is further configured to, after collecting the first historical operating data of each of the multiple devices, the device intelligent management method further includes: obtaining the energy consumption standard of each device under the current production conditions based on the first historical operating data.

[0087] In some embodiments of this application, the acquisition module 403 is further configured to clean the first historical operating data to obtain cleaned first historical operating data; and to determine the energy consumption standard based on the median of the cleaned first historical operating data.

[0088] In some embodiments of this application, the processing module 404 is further configured to periodically calculate the energy consumption standard of each device under the same production conditions to obtain historical energy consumption standards; and update the energy consumption standard of each device under the current production conditions based on the minimum value in the historical energy consumption standards.

[0089] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. As shown in the figure, the computer device 1 can be a server, for example, a central server, an edge server, or a local server in a local data center. Each computer device 1 may include a communication module 101, a memory 102, a processor 103, an input / output (I / O) interface 104, and a bus 105. The processor 103 is coupled to the communication interface 101, the memory 102, and the I / O interface 104 via the bus 105.

[0090] Communication module 101 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more wired communication solutions such as Universal Serial Bus (USB) and Controller Area Network (CAN). The wireless communication module may provide one or more wireless communication solutions such as Wireless Fidelity (Wi-Fi), Bluetooth (BT), mobile communication networks, Frequency Modulation (FM), Near Field Communication (NFC), and Infrared (IR).

[0091] Memory 102 may include one or more random access memory (RAM) and one or more non-volatile memory (NVM). The RAM can be directly read and written by the processor 103 and can be used to store executable programs (such as machine instructions) of the operating system or other running programs, as well as user and application data. The RAM may include static random-access memory (SRAM), dynamic random-access memory (DRAM), synchronous dynamic random-access memory (SDRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM), etc.

[0092] Non-volatile memory can also store executable programs and user and application data, and can be pre-loaded into random access memory for direct reading and writing by the processor 103. Non-volatile memory can include disk storage devices and flash memory.

[0093] Memory 102 is used to store one or more computer programs. The one or more computer programs are configured to be executed by processor 103. The one or more computer programs include multiple instructions, which, when executed by processor 103, can implement a model training method and a contract clause retrieval method that are executed on computer device 1.

[0094] In other embodiments, the computer device 1 further includes an external memory interface for connecting to an external memory to expand the storage capacity of the computer device 1.

[0095] Processor 103 may include one or more processing units, such as application processor (AP), modem processor, graphics processing unit (GPU), image signal processor (ISP), controller, video codec, digital signal processor (DSP), baseband processor, and / or neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0096] Processor 103 provides computing and control capabilities, for example, processor 103 is used to execute computer programs stored in memory 102.

[0097] I / O interface 104 is used to provide a channel for user input or output. For example, I / O interface 104 can be used to connect various input and output devices, such as mouse, keyboard, touch device, display screen, etc., so that users can enter information or visualize information.

[0098] Bus 105 is used at least to provide a channel for communication between communication modules 101, memory 102, processor 103, and I / O interface 104 in computer device 1.

[0099] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the computer device 1. In other embodiments of this application, the computer device 1 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0100] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can refer to the methods in the above embodiments of this application.

[0101] The computer-readable storage medium can be the internal memory of the electronic device described in the above embodiments, such as the hard disk or memory of the electronic device. Alternatively, the computer-readable storage medium can be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device.

[0102] In some embodiments, the computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, etc.; and the data storage area may store data created based on the use of the electronic device, etc.

[0103] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0104] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0105] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0106] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0107] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for intelligent equipment management, characterized in that, include: Pre-store equipment operation and maintenance knowledge base and preset energy consumption standards; Collect the first historical operating data of each of multiple devices; Monitor the real-time energy consumption of each of the multiple devices and compare it with the energy consumption standard; If it is determined that the real-time energy consumption does not meet the energy consumption standard, the second historical operating data of the abnormal device within a preset historical period is obtained. The second historical operating data is analyzed using a causal inference algorithm. The causal effect value of the real-time energy consumption is determined by quantifying each causal variable. Based on the causal effect value, the reasons why the real-time energy consumption does not meet the energy consumption standard are determined. Based on the reasons for not meeting the energy consumption standards, the pre-stored equipment operation and maintenance knowledge base is queried to obtain the corresponding energy-saving operation strategy; Based on the energy consumption standard and the first historical operating data, the energy efficiency assessment result of each device is predicted in a future preset time window using a prediction model; Set the scheduling priority factor for each device based on the energy efficiency assessment results; as well as The production schedule is adjusted based on the scheduling priority factor and the energy-saving operation strategy.

2. The intelligent equipment management method according to claim 1, characterized in that, The step of analyzing the second historical operating data using a causal inference algorithm, determining the causal effect value of the real-time energy consumption by quantifying each causal variable, and determining the reasons why the real-time energy consumption does not meet the energy consumption standard based on the causal effect value includes: The second set of historical operational data is preprocessed to obtain a set of variables for causal analysis; Based on the conditional independence test of the variables in the variable set, potential causal links between variables are screened. Perform a confusion factor control test on the causal links to obtain a set of valid causal links; A causal graph is constructed based on the set of effective causal links, and regression analysis is used to quantify each causal variable to determine the causal effect value of the real-time energy consumption; and The reasons for the deviation of real-time energy consumption from the energy consumption standard are determined by sorting the causal effect values ​​according to their magnitude.

3. The intelligent equipment management method according to claim 2, characterized in that, The method of using regression analysis to quantify the causal effect of each causal variable on the energy consumption outcome variable includes: For each valid causal link in the set of valid causal links, a regression model is constructed and solved with the energy consumption variable as the dependent variable and the corresponding causal variable and other control variables determined according to the causal diagram as independent variables. The regression coefficient of the causal variable is determined as the causal effect value.

4. The intelligent equipment management method according to claim 3, characterized in that, The prediction of the energy efficiency assessment results of the device in a future preset time window using a predictive model includes: Acquire real-time energy consumption data, processing status data, tool status data, and equipment alarm data of the device; Clustering the alarm data of the equipment yields the corresponding energy consumption impact factors; The energy consumption influencing factors, the real-time energy consumption data, the machining status data, and the tool status data are input into a pre-trained multivariate time-series prediction model; and Obtain the energy efficiency assessment results of the device in a future preset time window, output by the multivariate time series prediction model.

5. The intelligent equipment management method according to claim 1, characterized in that, After collecting the first historical operating data of each of the multiple devices, the intelligent device management method further includes: The energy consumption standard of each device under the current production conditions is obtained based on the first historical operating data.

6. The intelligent equipment management method according to claim 5, characterized in that, The energy consumption standard for each device under the current production conditions, obtained based on the first historical operating data, includes: The first historical running data is cleaned to obtain the cleaned first historical running data. The energy consumption standard is determined based on the median of the first historical operating data after the cleaning.

7. The intelligent equipment management method according to claim 5, characterized in that, The intelligent equipment management method also includes: Periodically calculate the energy consumption standard of each device under the same production conditions to obtain the historical energy consumption standard; The energy consumption standard of each device under the current production conditions is updated based on the minimum value in the historical energy consumption standards.

8. An intelligent equipment management device, characterized in that, include: The configuration module is used to pre-store the equipment operation and maintenance knowledge base and preset energy consumption standards; The monitoring module is used to collect the first historical operating data of each of the multiple devices; The monitoring module is also used to monitor the real-time energy consumption of each of the plurality of devices and compare it with the energy consumption standard; The acquisition module is used to acquire second historical operating data of the abnormal device within a preset historical period when it is determined that the real-time energy consumption does not meet the energy consumption standard. The processing module is used to analyze the second historical operating data using a causal inference algorithm, determine the causal effect value of the real-time energy consumption by quantifying each causal variable, and determine the reason why the real-time energy consumption does not meet the energy consumption standard based on the causal effect value. The processing module is also used to query the pre-stored equipment operation and maintenance knowledge base according to the reasons for not meeting the energy consumption standards, and obtain the corresponding energy-saving operation strategy; The processing module is also used to predict the energy efficiency assessment result of each device in a future preset time window based on the energy consumption standard and the first historical operating data using a prediction model. The setting module is further configured to set the scheduling priority factor for each device based on the energy efficiency assessment results; and The processing module is also used to adjust the production scheduling plan according to the scheduling priority factor and the energy-saving operation strategy.

9. A computer device, characterized in that, The computer device includes a processor and a memory, wherein the processor executes a computer program stored in the memory to implement the device intelligent management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the device intelligent management method as described in any one of claims 1 to 7.

Images