Performance evaluation methods, devices, electronic equipment and storage media

Abstract

This disclosure relates to the field of information processing technology, and in particular to a performance evaluation method, apparatus, electronic device, and storage medium. The performance evaluation method includes: acquiring a sequence of performance parameters corresponding to each of a plurality of steel billets; filtering at least one target performance parameter based on a performance parameter threshold; determining at least one dataset corresponding to each steel billet based on the at least one target performance parameter and a preset interval; determining the extreme values ​​in each dataset corresponding to each steel billet based on the magnitude of the performance parameters in each dataset corresponding to each steel billet; and determining a first distribution of the extreme values ​​corresponding to a plurality of steel billets based on the extreme values ​​corresponding to each steel billet. The performance evaluation method provided by the embodiments of this disclosure can reduce the correlation between the distribution of the dataset and time, thereby obtaining a more accurate first distribution. In addition, the first distribution of the embodiments of this disclosure is established by extreme values, which can improve the representativeness of the performance evaluation results of the steel rolling process.

Description

Technical Field

[0001] This disclosure relates to the field of information processing technology, and in particular to a performance evaluation method, apparatus, electronic device, and storage medium. Background Technology

[0002] Performance evaluation is a crucial task in steel rolling process monitoring. The performance parameters of steel billets during rolling are essential for determining product quality, and these parameters are closely related to the billet's performance during the rolling process. Rolling process performance can be divided into multiple stages involving different machines and different workers, depending on the billet's processing method. Machine malfunctions or worker errors can negatively impact the billet's performance parameters. In other words, timely monitoring of the rolling process's performance is beneficial for optimizing the performance parameters of subsequently processed billets. Therefore, how to better evaluate the performance of the rolling process is a critical technical problem that developers urgently need to solve. Summary of the Invention

[0003] This disclosure proposes a performance evaluation technique.

[0004] According to one aspect of this disclosure, a performance evaluation method is provided, the method comprising: acquiring a performance parameter sequence corresponding to each of a plurality of steel billets; wherein, the performance parameter sequence corresponding to each steel billet includes a plurality of performance parameters of the steel billet arranged in chronological order of acquisition time; filtering at least one target performance parameter in the performance parameter sequence corresponding to each steel billet according to a performance parameter threshold; determining at least one dataset corresponding to each steel billet according to the at least one target performance parameter corresponding to each steel billet and a preset interval; wherein, each dataset includes at least one target performance parameter; determining the extreme value in each dataset corresponding to each steel billet according to the magnitude of the performance parameter in each dataset corresponding to each steel billet; and determining a first distribution of the extreme values ​​corresponding to a plurality of steel billets over time according to the extreme values ​​in each dataset corresponding to each steel billet; wherein, the first distribution is used to evaluate the performance of the steel rolling process.

[0005] In one possible implementation, determining at least one dataset corresponding to each steel billet based on at least one target performance parameter and a preset interval for each steel billet includes: for each target performance parameter in the at least one target performance parameter corresponding to each steel billet, if none of the performance parameters within the preset interval following the target performance parameter in the performance parameter sequence corresponding to the steel billet are target performance parameters, then taking the target performance parameter and the performance parameters within the preset interval as a dataset.

[0006] In one possible implementation, determining at least one dataset corresponding to each steel billet based on at least one target performance parameter and a preset interval for each steel billet includes: for each target performance parameter among the at least one target performance parameters corresponding to each steel billet, if the performance parameters within the preset interval following the target performance parameter in the performance parameter sequence corresponding to the steel billet include other target performance parameters, and the performance parameters within the preset interval following the last target performance parameter among the other target performance parameters are not target performance parameters, then the target performance parameter to the last target performance parameter and the performance parameters within the preset interval are treated as a dataset.

[0007] In one possible implementation, the performance evaluation method further includes: performing a goodness-of-fit test on the first distribution to obtain a goodness-of-fit index corresponding to the first distribution; if the goodness-of-fit index is greater than a preset threshold, adjusting at least one of the performance parameter threshold and the preset interval, and regenerating multiple first distributions corresponding to steel billets based on the adjusted performance parameter threshold and / or the adjusted preset interval, until the goodness-of-fit index corresponding to the regenerated first distribution is less than or equal to the preset threshold.

[0008] In one possible implementation, the performance evaluation method further includes: acquiring multiple current performance parameters corresponding to the billet to be tested and time periods corresponding to the multiple current performance parameters; determining at least one dataset corresponding to the billet to be tested based on the performance parameter thresholds and the multiple current performance parameters; determining the extreme values ​​in each dataset corresponding to the billet to be tested based on the at least one dataset corresponding to the billet to be tested; and comparing the extreme values ​​in each dataset corresponding to the billet to be tested with the extreme values ​​corresponding to the time periods in the first distribution to obtain the performance of the rolling process corresponding to the billet to be tested.

[0009] In one possible implementation, the performance evaluation method further includes: determining the maximum dataset length corresponding to each steel billet based on the length of each dataset corresponding to each steel billet; sequentially arranging the maximum dataset lengths corresponding to each steel billet according to the time sequence in which multiple steel billets are collected to obtain a data length sequence; and determining a second distribution of the maximum dataset lengths corresponding to multiple steel billets over time based on the data length sequence; wherein the second distribution is used to evaluate the performance of the steel rolling process.

[0010] In one possible implementation, the performance evaluation method further includes: acquiring multiple current performance parameters corresponding to the billet to be tested and time periods corresponding to the multiple current performance parameters; determining at least one dataset corresponding to the billet to be tested based on the performance parameter thresholds and the multiple current performance parameters; determining the extreme values ​​in each dataset corresponding to the billet to be tested based on the at least one dataset corresponding to the billet to be tested; determining the maximum dataset length corresponding to the billet to be tested based on the length of each dataset corresponding to the billet to be tested; comparing the extreme values ​​in each dataset corresponding to the billet to be tested with the extreme values ​​corresponding to the time periods in the first distribution, and comparing the maximum dataset length corresponding to the billet to be tested with the maximum dataset length corresponding to the time periods in the second distribution, to obtain the performance of the rolling process corresponding to the billet to be tested.

[0011] According to one aspect of this disclosure, a performance evaluation device is provided, comprising: a performance parameter sequence acquisition module for acquiring a performance parameter sequence corresponding to each of a plurality of steel billets; wherein the performance parameter sequence corresponding to each steel billet includes a plurality of performance parameters of the steel billet arranged in the order of acquisition time; a target performance parameter screening module for screening at least one target performance parameter in the performance parameter sequence corresponding to each steel billet according to a performance parameter threshold; a dataset determination module for determining at least one dataset corresponding to each steel billet according to at least one target performance parameter corresponding to each steel billet and a preset interval; wherein each dataset includes at least one target performance parameter; an extreme value determination module for determining the extreme value in each dataset corresponding to each steel billet according to the magnitude of the performance parameter in each dataset corresponding to each steel billet; and a first distribution determination module for determining a first distribution of the extreme values ​​corresponding to a plurality of steel billets over time according to the extreme values ​​in each dataset corresponding to each steel billet; wherein the first distribution is used to evaluate the performance of the steel rolling process.

[0012] According to one aspect of this disclosure, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the performance evaluation method described above.

[0013] According to one aspect of this disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the above-described performance evaluation method.

[0014] In this embodiment, a performance parameter sequence corresponding to each of multiple steel billets can be obtained. Then, based on a performance parameter threshold, at least one target performance parameter is selected from the performance parameter sequence corresponding to each steel billet. Next, based on the at least one target performance parameter corresponding to each steel billet and a preset interval, at least one dataset corresponding to each steel billet is determined. Then, based on the magnitude of the performance parameters within each dataset corresponding to each steel billet, the extreme values ​​within each dataset corresponding to each steel billet are determined. Finally, based on the extreme values ​​of each dataset corresponding to each steel billet, a first distribution of the extreme values ​​corresponding to multiple steel billets over time is determined. The performance evaluation method provided in this embodiment can reduce the correlation between the distribution of datasets and time, thereby obtaining a more accurate first distribution. Furthermore, the first distribution in this embodiment is established based on extreme values, which can improve the representativeness of the performance evaluation results of the steel rolling process.

[0015] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0017] Figure 1 A flowchart of a performance evaluation method provided according to an embodiment of this disclosure is shown.

[0018] Figure 2 A block diagram of a performance evaluation apparatus provided according to an embodiment of the present disclosure is shown.

[0019] Figure 3 A block diagram of an electronic device provided according to an embodiment of the present disclosure is shown. Detailed Implementation

[0020] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0021] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0022] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0023] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0024] See Figure 1 , Figure 1 A flowchart of a performance evaluation method provided according to an embodiment of this disclosure is shown, in conjunction with... Figure 1 As shown, the performance evaluation method includes:

[0025] Step S100: Obtain the performance parameter sequence corresponding to each of the multiple steel billets. The performance parameter sequence for each steel billet includes multiple performance parameters of that steel billet arranged in chronological order of acquisition. Exemplarily, this embodiment does not limit the specific number of multiple steel billets, which can be determined by the developer according to actual needs. The performance parameters in each performance parameter sequence are of the same type. In one example, the types of performance parameters may include dimensional and shape indicators such as finished product thickness, finished product crown, and finished product flatness, as well as processing parameters such as finishing mill exit temperature and coiling temperature. This embodiment does not impose limitations here, and the specific types of performance parameters corresponding to the performance parameter sequence can be set by the developer and measured using sensors such as temperature sensors, pressure sensors, and displacement sensors in related technologies. Exemplarily, considering the accuracy of the final generated first distribution, steel billets from the same batch (e.g., the same steel grade, the same billet specification, and the same processing specification) can be used as the multiple steel billets.

[0026] Step S200: Based on the performance parameter threshold, at least one target performance parameter is selected from the performance parameter sequence corresponding to each steel billet. Exemplarily, the selection process for the performance parameter threshold is not limited in this embodiment of the disclosure; it can be set by developers based on practical experience, or according to preset rules, or it can be a fixed default value that can be compared with the performance parameters. In practical application scenarios, the performance parameter threshold may not be the performance parameter corresponding to when the steel billet is unqualified, but rather the performance parameter corresponding to when the steel billet is close to being unqualified. That is, the performance parameter threshold corresponding to a certain type of performance parameter can be located between the superior performance parameter and the unqualified performance parameter corresponding to that type of performance parameter of the steel billet. For example: Here, the finished product thickness is used as a performance parameter. If 5mm is considered the benchmark for unqualified and 3.5mm is considered the benchmark for superior, then the performance parameter threshold can be 4mm. In a practical scenario, if the finished product thickness of a steel billet remains above 4mm for a period of time, even though it does not exceed 5mm, it can still prove that the performance of the steel billet's rolling process may have a problem. For example, the filtering described above can be expressed as comparing the performance parameters in the performance parameter sequence with the performance parameter threshold. If the performance parameter threshold is the upper limit of the performance parameters, the performance parameters that exceed the threshold are taken as the target performance parameters. If the performance parameter threshold is the lower limit, the performance parameters that do not exceed the threshold are taken as the target performance parameters. The specific implementation depends on the actual needs of the developers, and this disclosure embodiment does not impose any limitations.

[0027] Step S300: Based on at least one target performance parameter corresponding to each steel billet and a preset interval, determine at least one dataset corresponding to each steel billet. Each dataset includes at least one target performance parameter. Exemplarily, the selection process for the preset interval is not limited in this embodiment; it can be set by developers based on practical experience, according to preset rules, or a fixed default value. This embodiment reduces the correlation between the dataset and time by using performance parameter thresholds and preset intervals to construct the dataset, which is beneficial to the accuracy of generating the subsequent first distribution, especially when the first distribution conforms to the generalized Pareto distribution (refer to the limitations of using the generalized Pareto distribution in related technologies, i.e., the generalized Pareto distribution cannot be directly used when there is time correlation between datasets or when it is non-stationary; this embodiment will not elaborate on this).

[0028] In one possible implementation, step S300 may include: for each target performance parameter in at least one target performance parameter corresponding to each billet, if none of the performance parameters within a preset interval following the target performance parameter in the performance parameter sequence corresponding to the billet are target performance parameters, then the target performance parameter and the performance parameters within the preset interval are treated as a dataset. Continuing the previous example, using 4mm as the performance parameter threshold, and assuming the performance parameter sequence in the billet is {3.1, 3.2, 5.6, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, 3.7}, since 5.6mm exceeds 4mm, the target performance parameter corresponding to the billet can be considered to be 5.6. If the preset interval is 3, then it is determined whether the three performance parameters following 5.6 are target performance parameters. In this example, the three performance parameters following 5.6 are 3.4, 3.5, and 3.6, none of which are target performance parameters, so {5.6, 3.4, 3.5, 3.6} can be treated as a dataset.

[0029] In one possible implementation, step S300 may include: for each target performance parameter in at least one target performance parameter corresponding to each billet, if the performance parameters within a preset interval after the target performance parameter in the performance parameter sequence corresponding to the billet include other target performance parameters, and the performance parameters within the preset interval after the last target performance parameter among the other target performance parameters are not target performance parameters, then the target performance parameter to the last target performance parameter and the performance parameters within the preset interval are treated as a dataset. For example, using 4mm as the performance parameter threshold mentioned above, the performance parameter sequence in the billet is {3.1, 3.2, 5.6, 3.4, 5.4, 5.7, 3.7, 3.8, 3.9, 3.7, 3.1, 3.2, 5.5, 3.4}. Since 5.6mm, 5.7mm, and 5.5mm all exceed 4mm, the target performance parameters corresponding to the billet can be considered to be 5.6, 5.7, 5.4, and 5.5. If the preset interval is 3, then... After determining the target performance parameter (taking 5.6 as an example), the performance parameters within a preset interval include other target performance parameters (i.e., {5.6, 3.4, 5.4, 5.7} includes 5.4 and 5.7). Therefore, the range from 5.6 to 5.7 (5.7 being the last target performance parameter among 5.4 and 5.7) and the three performance parameters after 5.7 are grouped into a dataset, namely {5.6, 3.4, 5.4, 5.7, 3.7, 3.8, 3.9}. Since 5.5 is also a target performance parameter, and there is no target performance parameter among the three performance parameters after 5.5 (there is only one after 5.5, 3.4, which is the last performance parameter in the sequence, satisfying the condition that no target performance parameter exists), {5.5, 3.4} is also grouped into a dataset. In this example, at least one dataset corresponding to the above-mentioned billet includes: {5.6, 3.4, 5.4, 5.7, 3.7, 3.8, 3.9} and {5.5, 3.4}.

[0030] Continue reading Figure 1 Step S400: Based on the magnitude of the performance parameters within each dataset corresponding to each steel billet, determine the extreme values ​​in each dataset corresponding to each steel billet. For example, the extreme values ​​can be either maximum or minimum values, depending on whether the performance parameter threshold is an upper or lower limit. If the performance parameter threshold is an upper limit, the extreme value is a maximum; if the performance parameter threshold is a lower limit, the extreme value is a minimum. For example, using the dataset {5.6, 3.4, 5.4, 5.7, 3.7, 3.8, 3.9} as an example, in this example, a larger performance parameter is more likely to be unqualified. Therefore, 4mm is the upper limit of the performance parameter, and the maximum value 5.7 can be taken as the extreme value of this dataset.

[0031] Step S500: Based on the extreme values ​​of each dataset corresponding to each steel billet, determine a first distribution of the extreme values ​​of multiple steel billets distributed over time. This first distribution is used to evaluate the performance of the rolling process. For example, the extreme values ​​can be fitted using a Generalized Pareto Distribution (GPD) from related technologies to obtain the first distribution. The specific generation method of the first distribution is not detailed here. In one example, after obtaining the first distribution, the distributions corresponding to several steel billets to be tested can be determined, and the two can be compared to determine the performance of the rolling process of the several steel billets to be tested. For example, if the difference in the distributions is higher than a threshold, it is considered that the rolling process performance of the several steel billets to be tested is poor, and the rolling-related machines may have errors or the workers may have made operational mistakes. In another example, after obtaining the first distribution, the extreme value corresponding to a steel billet to be tested and the time when the extreme value occurred can also be determined. Then, the extreme value is compared with the extreme values ​​in the first distribution that correspond to the time mentioned above (e.g., the same; considering that the recurrence period of the extreme value can also be expressed as a correspondence, this embodiment of the disclosure does not impose any limitations here). If the difference between the extreme values ​​is higher than a threshold, it is considered that the rolling process performance of the steel billet to be tested is poor, and the rolling-related machines may have made errors or the workers have made operational mistakes. For example, continuing the previous example, at least one dataset corresponding to the steel billet includes: {5.6, 3.4, 5.4, 5.7, 3.7, 3.8, 3.9} and {5.5, 3.4}. Then, the extreme value in {5.6, 3.4, 5.4, 5.7, 3.7, 3.8, 3.9} is 5.7, and the extreme value in {5.5, 3.4} is 5.5. It can be determined that the extreme values ​​of each dataset corresponding to the steel billet include 5.7 and 5.5. In practical applications, the performance evaluation of the steel rolling process in related technologies is obtained through continuous monitoring of performance parameters, resulting in weak representativeness of the final performance evaluation results. Furthermore, since the probability of extreme values ​​occurring during the steel rolling process is low, it is difficult to predict them using traditional probability distribution assumptions in related technologies. Therefore, this disclosure embodiment applies performance parameter thresholds and preset intervals sequentially to obtain a first distribution, which helps reduce the time-dependent correlation of extreme value distribution and thus obtains a more accurate performance evaluation result for the steel rolling process. Moreover, the first distribution in this disclosure embodiment is established based on extreme values, which improves the representativeness of the performance evaluation results. It should be understood that performance parameter thresholds and preset intervals reduce the time-dependent correlation of the obtained dataset and also contribute to improving the accuracy of the first distribution itself.

[0032] In one possible implementation, the performance evaluation method further includes: acquiring multiple current performance parameters corresponding to the billet to be tested and the time periods corresponding to the multiple current performance parameters. Exemplarily, the multiple current performance parameters corresponding to the billet to be tested have the same performance parameter types as the performance parameters in the performance parameter sequence corresponding to each billet among multiple billets. Then, based on the performance parameter thresholds and the multiple current performance parameters, at least one dataset corresponding to the billet to be tested is determined. Exemplarily, this step can be the same as the method for determining at least one dataset corresponding to each billet mentioned above, simply replacing the multiple performance parameters in the performance parameter sequence corresponding to each billet with the multiple current performance parameters corresponding to the billet to be tested as described above; this will not be elaborated upon in this embodiment. Then, based on the at least one dataset corresponding to the billet to be tested, the extreme values ​​in each dataset corresponding to the billet to be tested are determined. Exemplarily, this step can be the same as the method for determining the extreme values ​​in each dataset corresponding to each billet in step S400; this will not be elaborated upon in this embodiment. Finally, the extreme values ​​in each dataset corresponding to the steel billet to be tested are compared with the extreme values ​​corresponding to the time periods in the first distribution (e.g., they can be the same, and considering that the recurrence period of the extreme values ​​can also be represented as a correspondence, this embodiment of the disclosure does not impose any limitations here) to obtain the performance of the rolling process corresponding to the steel billet to be tested. For example, the above comparison (e.g., subtraction) can obtain a comparison difference degree (e.g., the difference value obtained by subtraction), and then the comparison difference degree is compared with a threshold to determine the performance of the detection process corresponding to the steel billet to be tested. For example: the comparison difference degree is less than the threshold and is better than the threshold. Combined with the actual application scenario, when the first distribution has been obtained, for the processing of each steel billet to be tested, multiple current performance parameters corresponding to the steel billet to be tested can be obtained and compared with the first distribution. When multiple current performance parameters indicate that there may be problems with the performance of the rolling process, the developers can investigate the possible problems, so that the steel billets processed subsequently will not be affected by abnormal rolling process performance, which is conducive to improving the rolling yield of steel billets.

[0033] In one possible implementation, a goodness-of-fit test is performed on the first distribution to obtain a goodness-of-fit index corresponding to the first distribution. Exemplarily, the goodness-of-fit index can be expressed as the p-value of the chi-square goodness-of-fit test in related technologies. The larger the p-value, the worse the first distribution. Exemplarily, the goodness-of-fit test can be performed using the Kolmogorov-Smirnov test (or KS test), Anderson-Darling test (or AD test), chi-square test, etc., in related technologies. The goodness-of-fit index can be expressed as the detection results corresponding to the above different test methods. For example, it can be expressed as the p-value of the chi-square goodness-of-fit test in related technologies; the larger the p-value, the worse the first distribution. If the goodness-of-fit index is greater than a preset threshold, at least one of the performance parameter threshold and the preset interval is adjusted. Based on the adjusted performance parameter threshold and / or the adjusted preset interval, multiple first distributions corresponding to steel billets are regenerated until the goodness-of-fit index corresponding to the regenerated first distribution is less than or equal to the preset threshold. For example, regenerating the first distribution corresponding to multiple steel billets includes: filtering at least one target performance parameter in the performance parameter sequence corresponding to each steel billet based on the adjusted or unadjusted performance parameter thresholds. Then, based on the at least one target performance parameter corresponding to each steel billet and the unadjusted or adjusted preset interval, at least one dataset corresponding to each steel billet is determined. Finally, based on the magnitude of the performance parameter in each dataset corresponding to each steel billet, the extreme value in each dataset corresponding to each steel billet is determined. For example, the above adjustment may include: increasing the performance parameter threshold by a first threshold, decreasing the performance parameter by a first threshold, increasing the preset interval by a second threshold, and decreasing the preset interval by a second threshold. The specific values ​​of the first threshold and the second threshold are not limited in this embodiment and can be determined by the developer according to actual needs. The adjustment is manifested as an increase or decrease, which can be determined by the trend of the goodness-of-fit index generated after adjustment compared to the goodness-of-fit index generated before adjustment. For example, in this example, a larger goodness-of-fit index indicates a worse first distribution. If the goodness-of-fit index shows an increasing trend, it proves that the adjusted first distribution is worse than the original first distribution. In this case, the adjustment is changed to another type of adjustment, i.e., from increasing to decreasing, or from decreasing to increasing. It should be understood that if the preset interval and the performance parameter threshold are adjusted simultaneously, their adjustment methods can also be different. For example, the preset interval can be increased, and the performance parameter threshold can be decreased, or the preset interval can be decreased, and the performance parameter threshold can also be decreased, etc. The specific adjustment method can be determined by the developers, and this disclosure embodiment does not impose any limitations.

[0034] In one possible implementation, the performance evaluation method further includes determining the maximum dataset length corresponding to each steel billet based on the length of each dataset corresponding to each steel billet. For example, the length of each dataset can be represented by the number of performance parameters included in each dataset. Continuing with an example using a performance parameter threshold of 4 and a preset interval of 3, if the dataset corresponding to steel billet A includes dataset a{5, 2, 3, 4}, dataset b{5.2, 2.4, 4.4, 1.8, 1.7, 1.6}, and dataset c{4.4, 2, 3, 4}, then the length of dataset a is 4, the length of dataset b is 6, and the length of dataset c is 4, so the maximum dataset length corresponding to steel billet A is 6. Then, according to the time sequence in which multiple steel billets are collected, the maximum dataset lengths corresponding to each steel billet are sequentially arranged to obtain a data length sequence. For example, if the performance parameters are collected in the following order (or time sequence): billet A, billet B, and billet C, and the maximum dataset length for billet A is 6, for billet B it is 4, and for billet C it is 5, then the resulting data length sequence is {6, 4, 5}. Finally, based on this data length sequence, a second distribution of the maximum dataset lengths corresponding to multiple billets over time is determined. This second distribution is used to evaluate the performance of the rolling process. Exemplarily, the maximum dataset lengths can be fitted using the Generalized Extreme Value Distribution (GEV) from related technologies to obtain the second distribution. The specific generation method of the second distribution is not detailed in this embodiment.

[0035] In one possible implementation, the performance evaluation method further includes obtaining multiple current performance parameters corresponding to the billet to be tested and the time periods corresponding to the multiple current performance parameters. For example, the multiple current performance parameters corresponding to the billet to be tested have the same performance parameter types as the performance parameters in the performance parameter sequence corresponding to each billet among multiple billets. Then, based on the performance parameter threshold and the multiple current performance parameters, at least one dataset corresponding to the billet to be tested is determined. For example, this step can be the same as the method for determining at least one dataset corresponding to each billet mentioned above, simply replacing the multiple performance parameters in the performance parameter sequence corresponding to each billet with the multiple current performance parameters corresponding to the billet to be tested as described above; this will not be elaborated upon in this embodiment. Next, based on the at least one dataset corresponding to the billet to be tested, the extreme values ​​in each dataset corresponding to the billet to be tested are determined. For example, this step can be the same as the method for determining the extreme values ​​in each dataset corresponding to each billet in step S400; this will not be elaborated upon in this embodiment. Then, based on the length of each dataset corresponding to the billet to be tested, the length of the maximum dataset corresponding to the billet to be tested is determined. For example, the maximum dataset length corresponding to the steel billet to be tested can be represented by the number of performance parameters included in the dataset. Finally, the extreme values ​​in each dataset corresponding to the steel billet to be tested are compared with the extreme values ​​corresponding to the time period in the first distribution, and the maximum dataset length corresponding to the steel billet to be tested is compared with the maximum dataset length corresponding to the time period in the second distribution to determine the performance of the rolling process corresponding to the steel billet to be tested. For example, the above comparison (e.g., subtraction) can obtain a comparison difference degree (e.g., represented by the difference obtained by subtraction), and then the comparison difference degree is compared with a threshold to determine the performance of the detection process corresponding to the steel billet to be tested. For example: a comparison difference degree less than the threshold is considered poor, and a comparison difference degree greater than the threshold is considered good. For example, if at least one of the following conditions is met, the rolling process performance of the steel billet to be tested may be considered abnormal: the comparison difference degree between the first distribution and the extreme value corresponding to the steel billet to be tested is less than the threshold; the contrast difference between the second distribution and the maximum dataset length corresponding to the steel billet to be tested is less than the threshold. Based on practical application scenarios, given the first and second distribution scenarios, for each steel billet to be inspected, multiple current performance parameters corresponding to the steel billet can be obtained and compared with the first and second distribution scenarios. If multiple current performance parameters indicate potential problems in the rolling process, developers can investigate the potential problems, ensuring that the steel billets processed subsequently are not affected by abnormal rolling process performance, which is beneficial to improving the rolling yield of steel billets.

[0036] This disclosure provides a practical scenario for reference. First, initialize the threshold u (i.e., the performance parameter threshold mentioned above) and the minimum interval r between strings (i.e., the preset interval mentioned above). For the key performance index (i.e., the performance parameter mentioned above) X of the i-th billet... i ∈X, where X is a set of key performance indicators for several steel billets. Then, strings exceeding the threshold (i.e., the dataset mentioned above) are obtained by filtering based on a threshold and the minimum interval between strings. The threshold-exceeding string for the i-th steel billet can be represented as... in, These represent multiple threshold strings corresponding to the i-th steel billet. For the i-th continuous key performance index, J i k is the total number of data sets. j The term "logical order" has no practical meaning here. All the overthreshold strings of rolled steel billets are grouped into an overthreshold string block set A = {A1, ..., A...}. i A N}, where N is the total number of steel billets, which is converted into a threshold sequence. Then, for each threshold-exceeding string in A, its maximum excess (i.e., the extreme value mentioned above) is found, and an extreme value sequence is constructed. The extreme value sequence is fitted using a generalized Pareto distribution to obtain the estimated parameters. in, This represents the location parameter in the generalized Pareto distribution. is the scale parameter in the generalized Pareto distribution. The shape parameters in the generalized Pareto distribution are given. The generalized Pareto distribution (i.e., the first distribution case mentioned above) is constructed using these three parameters. Then, based on the estimated parameter values, a goodness-of-fit test is performed. If the test fails, the threshold u and the minimum interval r between strings are adjusted, and the above steps are repeated. If the test succeeds, the set of overthreshold string blocks A and the three parameters of the generalized Pareto distribution are output. For example, these three parameters can be estimated using methods such as maximum likelihood estimation or L-moment estimation in related technologies. For A in the overthreshold string block set A... i Choose the length of the longest string (the length of the string is also the length of the dataset mentioned above) as A. i The extreme value (i.e., the maximum dataset length mentioned above), that is Here, len is the length calculation function. Then, by arranging the extreme values ​​according to the rolling time sequence, we can obtain the extreme value sequence (i.e., the data length sequence mentioned above) Z = {z1...., z...} i , ..., z N Using a generalized extreme value distribution, the extreme value sequence Z is fitted to obtain the parameters. in, The location parameter of the generalized extreme value distribution. The scale parameter of the generalized extreme value distribution. The shape parameters of the generalized extreme value distribution, together with the shape parameters of the generalized extreme value distribution, constitute the generalized extreme value distribution (i.e., the second distribution case mentioned above). The generalized Pareto distribution and the generalized extreme value distribution can calculate the extreme values ​​of key performance indicators and the length of the threshold string under a given return period. In the online monitoring system with real-time online acquisition, extreme value samples of key performance indicators and extreme value samples of the threshold string length can be obtained (i.e., the extreme values ​​and the length of the maximum dataset corresponding to the steel billet to be tested mentioned above). By calculating the quantiles in related technologies, when the quantile reaches a certain level (e.g., 0.01, the specific value is not limited here and can be set by the developers), it is considered that the rolling process performance of the steel billet to be tested is abnormal and needs to be inspected, maintained or adjusted.

[0037] The performance evaluation method provided in this disclosure focuses on extreme cases that occur during the steel rolling process, evaluating the degree (i.e., extreme values) and duration (i.e., the maximum dataset length) of these extreme cases during generation, thereby providing auxiliary support for decision-making in operation and maintenance, process adjustments, etc. Furthermore, due to the generally low probability of extreme values ​​occurring during steel rolling and the dynamic nature of steel rolling itself, this disclosure improves the accuracy of performance evaluation by fitting the data using the first and second disclosed scenarios.

[0038] See Figure 2 , Figure 2 A block diagram of a performance evaluation apparatus provided according to an embodiment of the present disclosure is shown, in conjunction with... Figure 2 As shown in the embodiments of this disclosure, a performance evaluation device 100 is also provided. The performance evaluation device 100 includes: a performance parameter sequence acquisition module 110, used to acquire a performance parameter sequence corresponding to each of a plurality of steel billets; wherein, the performance parameter sequence corresponding to each steel billet includes a plurality of performance parameters of the steel billet arranged in the order of the time of acquisition; a target performance parameter filtering module 120, used to filter at least one target performance parameter in the performance parameter sequence corresponding to each steel billet according to a performance parameter threshold; a dataset determination module 130, used to determine at least one dataset corresponding to each steel billet according to at least one target performance parameter corresponding to each steel billet and a preset interval; wherein, each dataset includes at least one target performance parameter; an extreme value determination module 140, used to determine the extreme value in each dataset corresponding to each steel billet according to the magnitude of the performance parameter in each dataset corresponding to each steel billet; and a first distribution determination module 150, used to determine a first distribution of the extreme values ​​corresponding to a plurality of steel billets in the order of time according to the extreme values ​​in each dataset corresponding to each steel billet; wherein, the first distribution is used to evaluate the performance of the steel rolling process.

[0039] In one possible implementation, determining at least one dataset corresponding to each steel billet based on at least one target performance parameter and a preset interval for each steel billet includes: for each target performance parameter in the at least one target performance parameter corresponding to each steel billet, if none of the performance parameters within the preset interval following the target performance parameter in the performance parameter sequence corresponding to the steel billet are target performance parameters, then taking the target performance parameter and the performance parameters within the preset interval as a dataset.

[0040] In one possible implementation, determining at least one dataset corresponding to each steel billet based on at least one target performance parameter and a preset interval for each steel billet includes: for each target performance parameter among the at least one target performance parameters corresponding to each steel billet, if the performance parameters within the preset interval following the target performance parameter in the performance parameter sequence corresponding to the steel billet include other target performance parameters, and the performance parameters within the preset interval following the last target performance parameter among the other target performance parameters are not target performance parameters, then the target performance parameter to the last target performance parameter and the performance parameters within the preset interval are treated as a dataset.

[0041] In one possible implementation, the performance evaluation device further includes: a goodness-of-fit detection module, used to perform a goodness-of-fit test on the first distribution to obtain a goodness-of-fit index corresponding to the first distribution; if the goodness-of-fit index is greater than a preset threshold, adjusting at least one of the performance parameter threshold and the preset interval, and regenerating multiple first distributions corresponding to steel billets based on the adjusted performance parameter threshold and / or the adjusted preset interval, until the goodness-of-fit index corresponding to the regenerated first distribution is less than or equal to the preset threshold.

[0042] In one possible implementation, the performance evaluation device further includes: a first detection module, configured to acquire multiple current performance parameters corresponding to the billet to be tested and time periods corresponding to the multiple current performance parameters; determine at least one dataset corresponding to the billet to be tested based on the performance parameter thresholds and the multiple current performance parameters; determine the extreme values ​​in each dataset corresponding to the billet to be tested based on the at least one dataset corresponding to the billet to be tested; and compare the extreme values ​​in each dataset corresponding to the billet to be tested with the extreme values ​​corresponding to the time periods in the first distribution to obtain the performance of the rolling process corresponding to the billet to be tested.

[0043] In one possible implementation, the performance evaluation device further includes: a second distribution determination module, configured to determine the maximum dataset length corresponding to each steel billet based on the length of each dataset corresponding to each steel billet; to sequentially arrange the maximum dataset lengths corresponding to each steel billet according to the time sequence in which multiple steel billets are collected, thereby obtaining a data length sequence; and to determine a second distribution of the maximum dataset lengths corresponding to multiple steel billets over time based on the data length sequence; wherein the second distribution is used to evaluate the performance of the steel rolling process.

[0044] In one possible implementation, the performance evaluation device further includes: a second detection module, configured to acquire multiple current performance parameters corresponding to the billet to be tested and time periods corresponding to the multiple current performance parameters; determine at least one dataset corresponding to the billet to be tested based on the performance parameter thresholds and the multiple current performance parameters; determine the extreme values ​​in each dataset corresponding to the billet to be tested based on the at least one dataset corresponding to the billet to be tested; determine the maximum dataset length corresponding to the billet to be tested based on the length of each dataset corresponding to the billet to be tested; compare the extreme values ​​in each dataset corresponding to the billet to be tested with the extreme values ​​corresponding to the time periods in the first distribution, and compare the maximum dataset length corresponding to the billet to be tested with the maximum dataset length corresponding to the time periods in the second distribution, to obtain the performance of the rolling process corresponding to the billet to be tested.

[0045] It is understood that the various method embodiments mentioned above in this disclosure can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this disclosure will not elaborate further. Those skilled in the art will understand that in the above methods of specific implementation, the specific execution order of each step should be determined by its function and possible internal logic.

[0046] In addition, this disclosure also provides electronic devices, computer-readable storage media, and programs, all of which can be used to implement any of the performance evaluation methods provided in this disclosure. The corresponding technical solutions and descriptions are described in the corresponding descriptions in the method section and will not be repeated here.

[0047] This method is specifically technically related to the internal structure of computer systems and can solve technical problems of how to improve hardware computing efficiency or execution performance (including reducing data storage, reducing data transmission, and increasing hardware processing speed), thereby achieving technical effects that improve the internal performance of computer systems in accordance with natural laws.

[0048] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0049] This disclosure also proposes a computer-readable storage medium storing computer program instructions that, when executed by a processor, implement the above-described method. The computer-readable storage medium can be volatile or non-volatile.

[0050] This disclosure also proposes an electronic device, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the above-described method.

[0051] This disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device performs the above-described method.

[0052] Electronic devices can be provided as terminal devices, servers, or other forms of devices.

[0053] See Figure 3 As shown, Figure 3 A block diagram of an electronic device 1900 according to an embodiment of the present disclosure is shown. For example, the electronic device 1900 may be provided as a server or a terminal device. (Refer to...) Figure 3 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the methods described above.

[0054] Electronic device 1900 may also include a power supply component 1926 configured to perform power management of electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input / output interface 1958. Electronic device 1900 can operate on an operating system stored in memory 1932, such as Microsoft Server operating system (Windows Server). TM Apple's graphical user interface-based operating system (Mac OS X) TM ), a multi-user, multi-process computer operating system (Unix)TM Linux is a free and open-source Unix-like operating system. TM ), the open-source Unix-like operating system (FreeBSD) TM (or similar.)

[0055] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by a processing component 1922 of an electronic device 1900 to perform the above-described method.

[0056] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0057] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, (but not limited to) electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0058] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0059] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0060] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0061] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0062] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0063] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0064] The computer program product can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0065] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0066] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0067] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0068] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A performance evaluation method characterized by, The performance evaluation method includes: Obtain the performance parameter sequence corresponding to each of the multiple steel billets; wherein, the performance parameter sequence corresponding to each steel billet includes multiple performance parameters of the steel billet arranged in the order of the time they were collected; Based on the performance parameter threshold, at least one target performance parameter is selected from the performance parameter sequence corresponding to each steel billet; Based on at least one target performance parameter corresponding to each steel billet and a preset interval, at least one dataset corresponding to each steel billet is determined; wherein, each dataset includes at least one target performance parameter; Based on the magnitude of the performance parameters within each dataset corresponding to each steel billet, determine the extreme values ​​in each dataset corresponding to each steel billet; Based on the extreme values ​​of each dataset corresponding to each steel billet, a first distribution of the extreme values ​​corresponding to multiple steel billets over time is determined; wherein, the first distribution is used to evaluate the performance of the steel rolling process. The step of determining at least one dataset corresponding to each steel billet based on at least one target performance parameter and a preset interval for each steel billet includes: for each target performance parameter in the at least one target performance parameter corresponding to each steel billet, if none of the performance parameters within the preset interval following the target performance parameter in the performance parameter sequence corresponding to the steel billet are target performance parameters, then the target performance parameter and the performance parameters within the preset interval are treated as a dataset. or, The step of determining at least one dataset corresponding to each steel billet based on at least one target performance parameter and a preset interval for each steel billet includes: for each target performance parameter in the at least one target performance parameter corresponding to each steel billet, if the performance parameters within the preset interval following the target performance parameter in the performance parameter sequence corresponding to the steel billet include other target performance parameters, and the performance parameters within the preset interval following the last target performance parameter among the other target performance parameters are not target performance parameters, then the target performance parameter to the last target performance parameter and the performance parameters within the preset interval are taken as a dataset.

2. The performance evaluation method of claim 1, wherein, The performance evaluation method also includes: Perform a goodness-of-fit test on the first distribution to obtain the goodness-of-fit index corresponding to the first distribution. If the goodness-of-fit index is greater than a preset threshold, at least one of the performance parameter threshold and the preset interval is adjusted. Based on the adjusted performance parameter threshold and / or the adjusted preset interval, multiple first distributions corresponding to steel billets are regenerated until the goodness-of-fit index corresponding to the regenerated first distribution is less than or equal to the preset threshold.

3. The performance evaluation method according to claim 1 or 2, characterized by, The performance evaluation method also includes: Obtain multiple current performance parameters corresponding to the steel billet to be tested, and the time period corresponding to the multiple current performance parameters; Based on the performance parameter threshold and the plurality of current performance parameters, at least one dataset corresponding to the steel billet to be detected is determined; Based on at least one dataset corresponding to the steel billet to be detected, determine the extreme values ​​in each dataset corresponding to the steel billet to be detected; By comparing the extreme values ​​in each dataset corresponding to the steel billet to be tested with the extreme values ​​corresponding to the time period in the first distribution, the performance of the rolling process corresponding to the steel billet to be tested can be obtained.

4. The performance evaluation method as described in claim 1 or 2, characterized in that, The performance evaluation method also includes: Determine the maximum dataset length for each steel billet based on the length of each dataset corresponding to each steel billet; Based on the time sequence in which multiple steel billets were collected, the maximum dataset length corresponding to each steel billet was arranged sequentially to obtain a data length sequence. Based on the data length sequence, a second distribution of the maximum dataset length corresponding to multiple steel billets is determined over time; wherein, the second distribution is used to evaluate the performance of the steel rolling process.

5. The performance evaluation method as described in claim 4, characterized in that, The performance evaluation method also includes: Obtain multiple current performance parameters corresponding to the steel billet to be tested, and the time period corresponding to the multiple current performance parameters; Based on the performance parameter threshold and the plurality of current performance parameters, at least one dataset corresponding to the steel billet to be detected is determined; Based on at least one dataset corresponding to the steel billet to be detected, determine the extreme values ​​in each dataset corresponding to the steel billet to be detected; The maximum dataset length corresponding to the steel billet to be detected is determined based on the length of each dataset corresponding to the steel billet to be detected. The extreme values ​​in each dataset corresponding to the steel billet to be tested are compared with the extreme values ​​corresponding to the time period in the first distribution, and the length of the maximum dataset corresponding to the steel billet to be tested is compared with the length of the maximum dataset corresponding to the time period in the second distribution to obtain the performance of the steel rolling process corresponding to the steel billet to be tested.

6. A performance evaluation device, characterized in that, The performance evaluation device includes: The performance parameter sequence acquisition module is used to acquire the performance parameter sequence corresponding to each steel billet among multiple steel billets; wherein, the performance parameter sequence corresponding to each steel billet includes multiple performance parameters of the steel billet arranged in the order of acquisition time; The target performance parameter filtering module is used to filter at least one target performance parameter in the performance parameter sequence corresponding to each billet based on the performance parameter threshold. The dataset determination module is used to determine at least one dataset corresponding to each steel billet based on at least one target performance parameter and a preset interval; wherein each dataset includes at least one target performance parameter; The extreme value determination module is used to determine the extreme value in each dataset corresponding to each steel billet based on the magnitude of the performance parameter in each dataset corresponding to each steel billet. The first distribution determination module is used to determine the first distribution of the extreme values ​​corresponding to multiple steel billets over time based on the extreme values ​​of each dataset corresponding to each steel billet; wherein, the first distribution is used to evaluate the performance of the steel rolling process. The dataset determination module is further used for: For each target performance parameter in at least one target performance parameter corresponding to each steel billet, if none of the performance parameters in the performance parameter sequence corresponding to the steel billet within a preset interval after the target performance parameter are target performance parameters, the target performance parameter and the performance parameters within the preset interval are taken as a dataset. or, For each target performance parameter in at least one target performance parameter corresponding to each steel billet, if the performance parameters within a preset interval after the target performance parameter in the performance parameter sequence corresponding to the steel billet include other target performance parameters, and the performance parameters within a preset interval after the last target performance parameter among the other target performance parameters are not target performance parameters, then the target performance parameter to the last target performance parameter and the performance parameters within the preset interval are treated as a dataset.

7. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the performance evaluation method according to any one of claims 1 to 5.

8. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the performance evaluation method according to any one of claims 1 to 5.

Images