An intelligent equipment value quantification method, device, equipment and storage medium

Abstract

The application provides a kind of intelligent equipment value quantification method, device, equipment and storage medium, it obtains original data containing system running mode signal, and based on the signal, key process parameters, yield and energy consumption data are separated into independent comparison data set associated with different control logic, so as to build a pure comparison environment with equipment, same period, only variable for control logic at data processing source, provide objective comparison basis for value proof;The application defines and quantifies the added value of intelligent equipment, effectively solves the problem that technical advantage is not intuitive enough.The target quantification index of the application, as a direct measure of the added value of intelligent technology, provides a direct and reliable input for converting it into specific business language, enabling customers to clearly and intuitively perceive technical investment returns.

Description

Technical Field

[0001] This invention relates to the field of industrial automation technology, and in particular to a method, apparatus, equipment and storage medium for quantifying the value of intelligent equipment. Background Technology

[0002] As a provider of intelligent equipment and technology services, we face two core challenges after promoting and delivering our products and services to customers: First, how to objectively, powerfully, and intuitively demonstrate the actual value that our products and services bring to customers (such as improved quality, reduced energy consumption, and increased efficiency); Second, how to accurately diagnose the root causes of problems and ensure the realization of the value of the technology when it is not fully applied.

[0003] Currently, suppliers typically provide screenshots of production operation interfaces, operational data reports, or simple pass rate statistics. However, this has significant shortcomings. In particular, existing technologies cannot provide a data foundation for strictly isolating and fairly comparing the intelligent control mode state and the basic control mode state under the same equipment and production conditions, which means that any comparison may be distorted due to data contamination.

[0004] Lack of persuasiveness: Simply showcasing the "pass rate" of one's own equipment fails to convey its value to customers because it lacks direct comparison with older equipment, industry standards, or different technical approaches.

[0005] Value is not intuitive: Data cannot be directly translated into business value that customers care about, such as "how much cost has been saved".

[0006] The technological advantages are not intuitive enough: it fails to highlight the overwhelming superiority of its intelligent technology compared to traditional technologies. There is a lack of a specially designed evaluation index system that can strip away the influence of basic performance and purely quantify the added value of intelligent algorithms.

[0007] Lack of diagnostic capabilities: When intelligent functions are not used, it is impossible to determine whether the problem is technical, personnel-related, or management-related, leading to an inability to intervene effectively. There is a lack of continuous quantitative monitoring of the application level of intelligent functions, as well as a lack of mechanisms to automatically trigger root cause analysis and value loss assessment when application is insufficient, leaving the service in a reactive state.

[0008] In view of this, it is necessary to propose a method, device, equipment and storage medium for quantifying the value of intelligent equipment in order to solve or at least alleviate the above-mentioned defects. Summary of the Invention

[0009] The main objective of this invention is to provide a method, apparatus, device, and storage medium for quantifying the value of intelligent equipment, so as to solve the technical problem that the existing technology cannot effectively quantify the value of intelligent equipment.

[0010] To achieve the above objectives, the present invention provides a method for quantifying the value of intelligent equipment, comprising the following steps: S1, acquire operating data from the intelligent equipment, the operating data including at least system operating mode signal, key process parameter data, output data and energy consumption data; wherein, the system operating mode signal is used to indicate the control mode state of the intelligent equipment during operation; S2, based on the system operation mode signal, perform mode separation processing on the key process parameter data, the output data and the energy consumption data to separate the key process parameter data, the output data and the energy consumption data into at least two independent comparison data sets; wherein, the first comparison data set is associated with the runtime segment driven by the preset basic control logic, and the second comparison data set is associated with the runtime segment driven by the intelligent optimization algorithm; S3. Based on the first comparison data set and the second comparison data set, perform comparative analysis to generate a target quantification index, wherein the target quantification index is used to quantify the performance improvement effect brought by the intelligent optimization algorithm relative to the preset basic control logic.

[0011] Preferably, step S2, which involves performing mode separation processing on the key process parameter data, the production data, and the energy consumption data based on the system operation mode signal, includes the following steps: S21, Analyze the system operation mode signal to continuously determine the control mode state of the intelligent equipment at each sampling moment; S22, based on the determined control mode state, the key process parameter data, the production data and the energy consumption data corresponding to the same sampling time are allocated and stored in real time to the comparison data set corresponding to the control mode state; The control mode state includes at least a first state and a second state. The first state corresponds to the runtime segment driven by the preset basic control logic, and the associated comparison data set is the first comparison data set. The second state corresponds to the runtime segment driven by the intelligent optimization algorithm, and the associated comparison data set is the second comparison data set.

[0012] Preferably, step S3 includes the following steps: Based on the key process parameter data in the first and second comparison data sets, the differences in process parameter control stability between the first and second comparison data sets are calculated and compared to generate a first quantization gain value, which is used as part of the target quantization index.

[0013] Preferably, the target quantification index further includes a key parameter excellence rate gain value, which is obtained through the following steps: For at least one key process parameter, an optimal process range corresponding to each key process parameter is preset. Based on the key process parameter data in the first comparison data set, a first cumulative metric is calculated for the key process parameter data falling into the corresponding optimal process interval; and based on the key process parameter data in the second comparison data set, a second cumulative metric is calculated for the key process parameter falling into the corresponding optimal process interval; wherein, the cumulative metric is the number of data points or the corresponding cumulative duration. Based on the total data volume or total duration of the first cumulative metric and the first comparison data set, calculate the first key parameter excellence rate; and based on the total data volume or total duration of the second cumulative metric and the second comparison data set, calculate the second key parameter excellence rate. Based on the first key parameter excellence rate and the second key parameter excellence rate, a key parameter excellence rate gain value is calculated, and the key parameter excellence rate gain value is used as part of the target quantification index; wherein, the key parameter excellence rate gain value is used to quantify the improvement of the intelligent optimization algorithm relative to the preset basic control logic in the dimension of process parameter excellence level.

[0014] Preferably, the target quantification index further includes a model energy efficiency ratio gain value, which is obtained through the following steps: Based on the production data and energy consumption data in the first comparison data set, the energy efficiency ratio of the first mode is calculated; wherein, the energy efficiency ratio of the first mode is the total energy consumption in the first comparison data set divided by the corresponding total production. Based on the production data and energy consumption data in the second comparison data set, the energy efficiency ratio of the second mode is calculated; wherein, the energy efficiency ratio of the second mode is the total energy consumption in the second comparison data set divided by the corresponding total production. Based on the first mode energy efficiency ratio and the second mode energy efficiency ratio, a mode energy efficiency ratio gain value is calculated, and the mode energy efficiency ratio gain value is used as part of the target quantification index; wherein, the mode energy efficiency ratio gain value is the relative change rate or absolute difference between the first mode energy efficiency ratio and the second mode energy efficiency ratio, which is used to quantify the improvement effect of the intelligent optimization algorithm on the energy efficiency dimension relative to the preset basic control logic.

[0015] Preferably, the method further includes the following steps: S4. Based on the system operation mode signal, calculate the proportion of the runtime driven by the intelligent optimization algorithm to the total runtime, and use the proportion as the intelligent control penetration rate. S5, compare the intelligent control penetration rate with a preset threshold, and trigger the diagnostic analysis process when the intelligent control penetration rate is continuously lower than the preset threshold for a duration exceeding a first preset time; wherein, the diagnostic analysis process includes a value loss assessment step: calculate the value loss quantification value based on the target quantitative index generated in step S3 and the intelligent control penetration rate.

[0016] Preferably, the diagnostic analysis process further includes the following steps: S52, analyze the switching sequence of the system operation mode signal and the system alarm records associated with the operation of the intelligent optimization algorithm, and classify the main reasons for the low penetration rate of the intelligent control into technical obstacles, operational obstacles or systemic obstacles according to the preset judgment rules. The determination rules include: if the frequency of critical alarms exceeds a first threshold during the period driven by the intelligent optimization algorithm, it is attributed to technical obstacles; if the frequency of switching to other modes initiated by operators exceeds a second threshold in the absence of critical alarms, it is attributed to operational obstacles; and if there are planned disabling records related to production management rules, it is attributed to systemic obstacles.

[0017] The present invention also provides a device for quantifying the value of intelligent equipment, used to perform the intelligent equipment value quantification method as described above, comprising: The data acquisition module is used to acquire operational data from the intelligent equipment. The operational data includes at least system operation mode signals, key process parameter data, output data, and energy consumption data. The system operation mode signals are used to indicate the control mode state of the intelligent equipment during operation. The data processing module is used to perform mode separation processing on the key process parameter data, the output data, and the energy consumption data based on the system operation mode signal, so as to separate the key process parameter data, the output data, and the energy consumption data into at least two independent comparison data sets; wherein, the first comparison data set is associated with the runtime segment driven by the preset basic control logic, and the second comparison data set is associated with the runtime segment driven by the intelligent optimization algorithm. The analysis and generation module is used to perform comparative analysis based on the first comparison data set and the second comparison data set to generate a target quantification index, wherein the target quantification index is used to quantify the performance improvement effect brought by the intelligent optimization algorithm relative to the preset basic control logic.

[0018] The present invention also provides a device for quantifying the value of intelligent equipment, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the intelligent equipment value quantification method described above.

[0019] The present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the intelligent equipment value quantification method described above.

[0020] Compared with the prior art, the present invention has the following beneficial effects: This invention provides a method, apparatus, device, and storage medium for quantifying the value of intelligent equipment. It acquires raw data containing system operation mode signals and, based on these signals, separates key process parameters, output, and energy consumption data into independent comparative data sets associated with different control logics. This constructs a pure comparative environment at the data processing source, with the same equipment, the same time period, and control logic as the sole variable, providing an objective basis for value verification. This application defines and quantifies the added value of intelligent equipment, effectively solving the problem of insufficiently intuitive technological advantages. Specifically, by performing comparative analysis, target quantitative indicators are generated. These indicators (such as gain values ​​in dimensions like stability, excellence rate, or energy efficiency ratio) strip away the influence of basic equipment performance, purely amplifying the performance improvement brought by intelligent algorithms. The target quantitative indicators of this invention, as a direct measure of the added value of intelligent technology, provide a direct and reliable input for translating it into specific business language, enabling customers to clearly and intuitively perceive the return on technology investment. Furthermore, this application can also combine quantified performance gain indicators to assess potential value loss, achieving proactive service and precise intervention. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating an embodiment of the present invention.

[0023] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0024] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0026] It should be noted that all directional indicators (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain selected posture (as shown in the figure). If the selected posture changes, the directional indicator will also change accordingly.

[0027] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. If the combination of technical solutions is contradictory or impossible to implement, such a combination should be considered non-existent and not within the scope of protection claimed by this invention.

[0028] Please see the appendix Figure 1 An embodiment of the present invention provides a method for quantifying the value of intelligent equipment, comprising the following steps: S1, acquire operating data from the intelligent equipment, the operating data including at least system operating mode signal, key process parameter data, output data and energy consumption data; wherein, the system operating mode signal is used to indicate the control mode state of the intelligent equipment during operation; The intelligent equipment in this application refers to industrial automation equipment or systems that integrate at least two levels of control logic. This step is the data input basis of the method. The operating data can be obtained in real time through a data acquisition agent deployed in the control system of the intelligent equipment. The system operating mode signal is a discrete state quantity, which comes directly from the host computer or algorithm module of the control system. In an optional embodiment, the control mode state is divided into three types: manual control mode (M), closed-loop automatic control mode (A), and intelligent control mode (I). The signal value "0" represents manual control mode (M), that is, the operator directly sets the output through the human-machine interface; "1" represents closed-loop automatic control mode (A), that is, the operation is maintained by preset basic control logic such as PID; "2" represents intelligent control mode (I), that is, the operation is driven by the advanced control algorithm to be evaluated (such as model predictive control, adaptive optimization algorithm).

[0029] Key process parameters are continuous analog or digital quantities, and can be derived from sensors on the production line (such as temperature sensors, pressure transmitters, and vision inspection systems). For example, in the steel sintering ignition furnace control scenario given later, key process parameters may include "ignition furnace temperature" and "exhaust gas oxygen content".

[0030] Production data typically comes from production line counters or work order records in the MES system, and is accumulated in units such as "pieces" or "tons". Energy consumption data comes from metering instruments such as smart meters and gas flow meters, which record the consumption of electricity, gas, etc. in real time.

[0031] S2, based on the system operation mode signal, perform mode separation processing on the key process parameter data, the output data and the energy consumption data to separate the key process parameter data, the output data and the energy consumption data into at least two independent comparison data sets; wherein, the first comparison data set is associated with the runtime segment driven by the preset basic control logic, and the second comparison data set is associated with the runtime segment driven by the intelligent optimization algorithm; The purpose of this step is to separate the mixed operational data according to the control logic context in which it was generated, thereby forming at least two independent sets of comparison data: a first set of comparison data and a second set of comparison data.

[0032] S3. Based on the first comparison data set and the second comparison data set, perform comparative analysis to generate a target quantification index, wherein the target quantification index is used to quantify the performance improvement effect brought by the intelligent optimization algorithm relative to the preset basic control logic.

[0033] The following description uses a specific embodiment as an example to illustrate the value quantification of a steel company's "intelligent sintering ignition furnace control system".

[0034] The first set of comparative data corresponds to the combustion process data collected under the closed-loop automatic control mode (A); the second set of comparative data corresponds to the data collected under the intelligent control mode (I).

[0035] (1) Comparison of stability dimensions: Calculate the standard deviation (σ) of the key process parameter "combustion temperature" in the two comparison datasets respectively. Standard deviation is a well-known indicator in statistics for measuring the volatility of data.

[0036] Temperature stability comparisons can be performed. For example, the stability coefficient (SC) can be calculated based on the standard deviation of the "combustion temperature" in the first and second comparison datasets. The stability characterization value is defined as the stability coefficient (SC), and its calculation formula is: SC = μ / (σ + δ). Where μ is the average value of the key process parameter data in the comparison dataset, σ is the standard deviation, and δ is a very small positive number much smaller than μ (e.g., 1 × 10⁻⁶). -6 μ (whose dimensions are consistent with μ) is used to prevent the denominator from being zero. SC is a dimensionless ratio; the larger the value, the smaller the relative fluctuation of the process parameters and the higher the stability under this mode.

[0037] Furthermore, the Model Performance Gain (MEG) is used as one of the target quantification indicators, and its formula is: MEG 稳定性 =(SC I - SC A ) / SC A ×100%, of which, SC I SC represents the stability coefficient under intelligent control mode (I). A This represents the stability coefficient under the basic automatic control mode (A). This indicator quantifies the improvement in control stability achieved by the intelligent optimization algorithm compared to basic control.

[0038] (2) Comparison of excellence dimensions, for example, setting the optimal process range for "oxygen content in exhaust gas of a certain air box" as [14%, 15%] (more stringent than the "qualified" range [13%, 14%]). Calculate the percentage of time that the data in the first and second comparison data sets falls within the optimal range.

[0039] The percentage of time the "oxygen content in exhaust gas from a certain windbox" data point falls within the optimal process range in the two comparative datasets was statistically analyzed to obtain the excellence rate of key parameters. By calculating the difference between the two datasets as the mode efficiency gain in this dimension, this indicator directly proves that the intelligent algorithm's ability to maintain process parameters at a top level has been significantly enhanced.

[0040] In a preferred embodiment, step S2, which involves performing mode separation processing on the key process parameter data, the production data, and the energy consumption data based on the system operation mode signal, includes the following steps: S21, parse the system operation mode signal to continuously determine the control mode state of the intelligent equipment at each sampling moment; for example, when the read signal value is "1", it is determined that the intelligent equipment is in the first state (i.e., closed-loop automatic control mode A) at the current moment; when the signal value is "2", it is determined to be in the second state (i.e., intelligent control mode I). A specific control mode state label is output at each sampling moment.

[0041] S22, based on the determined control mode state, the key process parameter data, the production data and the energy consumption data corresponding to the same sampling time are allocated and stored in real time to the comparison data set corresponding to the control mode state; The control mode state includes at least a first state and a second state. The first state corresponds to the runtime segment driven by the preset basic control logic, and the associated comparison data set is the first comparison data set. The second state corresponds to the runtime segment driven by the intelligent optimization algorithm, and the associated comparison data set is the second comparison data set.

[0042] In a preferred embodiment, step S3 includes the following steps: Based on the key process parameter data in the first and second comparison data sets, the differences in process parameter control stability between the first and second comparison data sets are calculated and compared to generate a first quantization gain value, which is used as part of the target quantization index.

[0043] Specifically, variance (or standard deviation) from mathematical statistics can be used as the core analytical tool. By using time series data of the same key process parameter (e.g., "combustion temperature") from the first comparative dataset (corresponding to basic automatic mode A) and the second comparative dataset (corresponding to intelligent mode I), two objective indicators that directly reflect the strength of the fluctuation of the process parameter under each mode can be calculated. The smaller the value, the more stable the production under that mode.

[0044] As mentioned earlier, stability can be characterized by calculating the stability coefficient (SC), and the mode effectiveness gain (MEG) can be calculated based on this coefficient. MEG is defined as the relative rate of change of the mode effectiveness gain in intelligent mode relative to the mode effectiveness gain in basic control mode. This percentage-based gain value directly and impactfully demonstrates the stability leap brought about by the intelligent algorithm, effectively addressing the issue of insufficiently intuitive technical advantages.

[0045] In a preferred embodiment, the target quantification index further includes the excellence rate of key parameters, which is obtained through the following steps: For at least one key process parameter, an optimal process range is preset for each key process parameter; wherein, the optimal process range is a numerical range that is more stringent than the acceptable range of the process parameter that ensures the basic qualification of the product, and its setting goal is to pursue the best process effect, such as the highest product quality, the lowest unit consumption, or the best reaction efficiency.

[0046] Based on the key process parameter data in the first comparison data set (associated with the basic control mode), a first cumulative metric is calculated to show that the key process parameter data falls into the corresponding optimal process range; and based on the key process parameter data in the second comparison data set (associated with the intelligent optimization algorithm mode), a second cumulative metric is calculated to show that the key process parameter falls into the corresponding optimal process range; wherein, the cumulative metric is the number of data points or the corresponding cumulative duration. Based on the total data volume or total duration of the first cumulative metric and the first comparison data set, calculate the first key parameter excellence rate; and based on the total data volume or total duration of the second cumulative metric and the second comparison data set, calculate the second key parameter excellence rate. Based on the first key parameter excellence rate and the second key parameter excellence rate, a key parameter excellence rate gain value is calculated, and the key parameter excellence rate gain value is used as part of the target quantification index; wherein, the key parameter excellence rate gain value is used to quantify the improvement of the intelligent optimization algorithm relative to the preset basic control logic in the dimension of process parameter excellence level.

[0047] The physical meaning of this excellence rate is the percentage of time that the process parameters are maintained at an excellent level under the corresponding control mode. The calculated gain value of the excellence rate of key parameters is used as part of the target quantitative index. The gain value of the excellence rate of key parameters directly and quantitatively characterizes the improvement of the intelligent optimization algorithm in its ability to drive the process parameters to reach and maintain an excellent level compared to the preset basic control logic.

[0048] In a preferred embodiment, the target quantification index further includes a model energy efficiency ratio gain value, which is obtained through the following steps: Based on the production data and energy consumption data in the first comparison data set, the energy efficiency ratio of the first mode is calculated; wherein, the energy efficiency ratio of the first mode is the total energy consumption in the first comparison data set divided by the corresponding total production. Based on the production data and energy consumption data in the second comparison data set, the energy efficiency ratio of the second mode is calculated; wherein, the energy efficiency ratio of the second mode is the total energy consumption in the second comparison data set divided by the corresponding total production. Specifically, the instantaneous energy consumption values ​​of all sampling points within the set can be accumulated. If the data is a cumulative value, the difference between the start and end times is taken. For example, by accumulating the increments of all meter readings, the total power consumption (unit: kWh) under this mode can be obtained. The corresponding production counts within this set are then accumulated to obtain the total output of qualified products under this mode (unit: tons, pieces).

[0049] For each set, calculate its Model Energy Efficiency Ratio (MER) using the formula: Model Energy Efficiency Ratio (MER) = Total Energy Consumption / Total Output. This indicator represents the average amount of energy consumed to produce one unit of qualified product under a specific control model. The lower the value, the higher the energy efficiency of the model.

[0050] Based on the first mode energy efficiency ratio and the second mode energy efficiency ratio, a mode energy efficiency ratio gain value is calculated, and the mode energy efficiency ratio gain value is used as part of the target quantification index; wherein, the mode energy efficiency ratio gain value is the relative change rate or absolute difference between the first mode energy efficiency ratio and the second mode energy efficiency ratio, which is used to quantify the improvement effect of the intelligent optimization algorithm on the energy efficiency dimension relative to the preset basic control logic.

[0051] The mode energy efficiency ratio gain value is presented as a percentage, which visually and impactfully demonstrates the degree of optimization of the intelligent algorithm in the energy efficiency dimension. This perfectly solves the problem of the lack of intuitiveness in the technical advantages and is more convincing than simply showing two energy consumption figures.

[0052] In a preferred embodiment, the method further includes the following steps: S4. Based on the system operation mode signal, calculate the proportion of the runtime driven by the intelligent optimization algorithm to the total runtime, and use the proportion as the intelligent control penetration rate. S5, compare the intelligent control penetration rate with a preset threshold (e.g., 70%), and trigger the diagnostic analysis process when the intelligent control penetration rate is continuously lower than the preset threshold for a duration exceeding a first preset time (e.g., 4 hours); wherein, the diagnostic analysis process includes a value loss assessment step: calculate the value loss quantification value based on the target quantitative index generated in step S3 and the intelligent control penetration rate.

[0053] As an example: Value loss = MEG × (1 - ICP) × V unit ×T; where MEG is the target quantification index generated in step S3, such as the gain value of the key parameter excellence rate or the gain value of the mode energy efficiency ratio. It represents the potential performance improvement per unit time of the intelligent mode relative to the basic mode. (1-ICP) is the proportion of runtime without using the intelligent optimization algorithm. V unitThis is a preset value conversion factor, with the dimension [value] / [time], for example, 'yuan / hour'. This factor is a parameter set based on the expected or historical economic benefits per unit time generated by the intelligent optimization algorithm, and can be determined by statistically analyzing historical data, calculating based on product and energy unit prices combined with a capacity model, or according to contractually agreed values. T is the evaluation period, i.e., the statistical period for calculating value loss. This formula can calculate the potential profits wasted due to the failure to use advanced technologies. The calculation results quantitatively reveal the potential profit losses caused by the insufficient application of intelligent functions, transforming technical management issues into intuitive economic indicators.

[0054] As an example of a diagnostic analysis process: When the system detects that the intelligent control penetration rate of a certain intelligent sintering ignition furnace is below a preset threshold (50%) for 8 consecutive hours, a diagnosis is automatically triggered. The system analyzes the system operation mode signal switching sequence and associated alarm records during this period. If it is found that the frequency of the "low gas pressure" alarm exceeds 3 times per hour during the 'intelligent mode' operation, it is attributed to a technical obstacle according to rules. If it is found that the operator manually switches to 'basic automatic mode' multiple times without critical alarms, it indicates that there is an operational obstacle. Based on this, the system can generate a diagnostic report containing the obstacle type and recommended measures.

[0055] In a preferred embodiment, the diagnostic analysis process further includes the following steps: S52, analyze the switching sequence of the system operation mode signal and the system alarm records associated with the operation of the intelligent optimization algorithm, and classify the main reasons for the low penetration rate of the intelligent control into technical obstacles, operational obstacles or systemic obstacles according to the preset judgment rules. The determination rules include: if the frequency of critical alarms exceeds a first threshold during the period driven by the intelligent optimization algorithm, it is attributed to technical obstacles; if the frequency of switching to other modes initiated by operators exceeds a second threshold in the absence of critical alarms, it is attributed to operational obstacles; and if there are planned disabling records related to production management rules, it is attributed to systemic obstacles.

[0056] By analyzing the switching sequences of system operation mode signals and associated system alarm records, and based on a set of preset judgment rules based on data frequency and logical correlation, the system performs classification judgments. This transforms the original troubleshooting process, which relied on manual experience, was time-consuming, and subjective, into an automated, data-driven analysis process. Through diagnosis and intervention, the system ensures that customers can truly use and effectively leverage intelligent technology, ultimately achieving the expected value and building long-term trust and cooperation.

[0057] The present invention also provides a device for quantifying the value of intelligent equipment, used to perform the intelligent equipment value quantification method as described above, comprising: The data acquisition module is used to acquire operational data from the intelligent equipment. The operational data includes at least system operation mode signals, key process parameter data, output data, and energy consumption data. The system operation mode signals are used to indicate the control mode of the intelligent equipment during operation. The data processing module is used to perform mode separation processing on the key process parameter data, the output data, and the energy consumption data based on the system operation mode signal, so as to separate the key process parameter data, the output data, and the energy consumption data into at least two independent comparison data sets; wherein, the first comparison data set is associated with the runtime segment driven by the preset basic control logic, and the second comparison data set is associated with the runtime segment driven by the intelligent optimization algorithm. The analysis and generation module is used to perform comparative analysis based on the first comparison data set and the second comparison data set to generate a target quantification index, wherein the target quantification index is used to quantify the performance improvement effect brought by the intelligent optimization algorithm relative to the preset basic control logic.

[0058] The present invention also provides a device for quantifying the value of intelligent equipment, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the intelligent equipment value quantification method described above.

[0059] The present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the intelligent equipment value quantification method described above.

[0060] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0061] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for quantifying the value of intelligent equipment, characterized in that, Includes the following steps: S1, acquire operating data from the intelligent equipment, the operating data including at least system operating mode signal, key process parameter data, output data and energy consumption data; wherein, the system operating mode signal is used to indicate the control mode state of the intelligent equipment during operation; S2, based on the system operation mode signal, perform mode separation processing on the key process parameter data, the output data and the energy consumption data to separate the key process parameter data, the output data and the energy consumption data into at least two independent comparison data sets; wherein, the first comparison data set is associated with the runtime segment driven by the preset basic control logic, and the second comparison data set is associated with the runtime segment driven by the intelligent optimization algorithm; S3. Based on the first comparison data set and the second comparison data set, perform comparative analysis to generate a target quantification index, wherein the target quantification index is used to quantify the performance improvement effect brought by the intelligent optimization algorithm relative to the preset basic control logic.

2. The method for quantifying the value of intelligent equipment according to claim 1, characterized in that, Step S2, which involves performing mode separation processing on the key process parameter data, the production data, and the energy consumption data based on the system operation mode signal, includes the following steps: S21, Analyze the system operation mode signal to continuously determine the control mode state of the intelligent equipment at each sampling moment; S22, based on the determined control mode state, the key process parameter data, the production data and the energy consumption data corresponding to the same sampling time are allocated and stored in real time to the comparison data set corresponding to the control mode state; The control mode state includes at least a first state and a second state. The first state corresponds to the runtime segment driven by the preset basic control logic, and the associated comparison data set is the first comparison data set. The second state corresponds to the runtime segment driven by the intelligent optimization algorithm, and the associated comparison data set is the second comparison data set.

3. The method for quantifying the value of intelligent equipment according to claim 2, characterized in that, Step S3 includes the following steps: Based on the key process parameter data in the first and second comparison data sets, the differences in process parameter control stability between the first and second comparison data sets are calculated and compared to generate a first quantization gain value, which is used as part of the target quantization index.

4. The method for quantifying the value of intelligent equipment according to any one of claims 1-3, characterized in that, The target quantitative indicator also includes the key parameter excellence rate gain value, which is obtained through the following steps: For at least one key process parameter, an optimal process range corresponding to each key process parameter is preset. Based on the key process parameter data in the first comparison data set, a first cumulative metric is calculated to show that the key process parameter data falls into the corresponding optimal process range. Based on the key process parameter data in the second comparison data set, a second cumulative metric is calculated to determine whether the key process parameters fall within the corresponding optimal process range; wherein, the cumulative metric is the number of data points or the corresponding cumulative duration. Based on the total data volume or total duration of the first cumulative metric and the first comparison data set, calculate the first key parameter excellence rate; and based on the total data volume or total duration of the second cumulative metric and the second comparison data set, calculate the second key parameter excellence rate. Based on the first key parameter excellence rate and the second key parameter excellence rate, a key parameter excellence rate gain value is calculated, and the key parameter excellence rate gain value is used as part of the target quantification index; wherein, the key parameter excellence rate gain value is used to quantify the improvement of the intelligent optimization algorithm relative to the preset basic control logic in the dimension of process parameter excellence level.

5. The method for quantifying the value of intelligent equipment according to claim 4, characterized in that, The target quantitative indicator also includes the model energy efficiency ratio gain value, which is obtained through the following steps: Based on the production data and energy consumption data in the first comparison data set, the energy efficiency ratio of the first mode is calculated; wherein, the energy efficiency ratio of the first mode is the total energy consumption in the first comparison data set divided by the corresponding total production. Based on the production data and energy consumption data in the second comparison data set, the energy efficiency ratio of the second mode is calculated; wherein, the energy efficiency ratio of the second mode is the total energy consumption in the second comparison data set divided by the corresponding total production. Based on the first mode energy efficiency ratio and the second mode energy efficiency ratio, a mode energy efficiency ratio gain value is calculated, and the mode energy efficiency ratio gain value is used as part of the target quantification index; wherein, the mode energy efficiency ratio gain value is the relative change rate or absolute difference between the first mode energy efficiency ratio and the second mode energy efficiency ratio, which is used to quantify the improvement effect of the intelligent optimization algorithm on the energy efficiency dimension relative to the preset basic control logic.

6. The method for quantifying the value of intelligent equipment according to claim 1, characterized in that, The method further includes the following steps: S4. Based on the system operation mode signal, calculate the proportion of the runtime driven by the intelligent optimization algorithm to the total runtime, and use the proportion as the intelligent control penetration rate. S5, compare the intelligent control penetration rate with a preset threshold, and trigger the diagnostic analysis process when the intelligent control penetration rate is continuously lower than the preset threshold for a duration exceeding a first preset time; wherein, the diagnostic analysis process includes a value loss assessment step: calculate the value loss quantification value based on the target quantitative index generated in step S3 and the intelligent control penetration rate.

7. The method for quantifying the value of intelligent equipment according to claim 6, characterized in that, The diagnostic analysis process also includes the following steps: S52, analyze the switching sequence of the system operation mode signal and the system alarm records associated with the operation of the intelligent optimization algorithm, and classify the main reasons for the low penetration rate of the intelligent control into technical obstacles, operational obstacles or systemic obstacles according to the preset judgment rules. The determination rules include: if the frequency of critical alarms exceeds a first threshold during the period driven by the intelligent optimization algorithm, it is attributed to technical obstacles; if the frequency of switching to other modes initiated by operators exceeds a second threshold in the absence of critical alarms, it is attributed to operational obstacles; and if there are planned disabling records related to production management rules, it is attributed to systemic obstacles.

8. A device for quantifying the value of intelligent equipment, characterized in that, include: The data acquisition module is used to acquire operational data from the intelligent equipment. The operational data includes at least system operation mode signals, key process parameter data, output data, and energy consumption data. The system operation mode signals are used to indicate the control mode state of the intelligent equipment during operation. The data processing module is used to perform mode separation processing on the key process parameter data, the output data, and the energy consumption data based on the system operation mode signal, so as to separate the key process parameter data, the output data, and the energy consumption data into at least two independent comparison data sets; wherein, the first comparison data set is associated with the runtime segment driven by the preset basic control logic, and the second comparison data set is associated with the runtime segment driven by the intelligent optimization algorithm. The analysis and generation module is used to perform comparative analysis based on the first comparison data set and the second comparison data set to generate a target quantification index, wherein the target quantification index is used to quantify the performance improvement effect brought by the intelligent optimization algorithm relative to the preset basic control logic.

9. A device for quantifying the value of intelligent equipment, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the intelligent equipment value quantification method as described in any one of claims 1 to 8.

10. A storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent equipment value quantification method as described in any one of claims 1 to 8.

Images