Fire-fighting building engineering facility production scheme remote diagnosis and analysis system

Abstract

The invention relates to the technical field of data identification, in particular to a fire-fighting building engineering facility production scheme remote diagnosis and analysis system, which comprises a data acquisition and transmission module, a data storage and management module and an anomaly detection and processing module, and is characterized in that the data acquisition and transmission module is used for acquiring enterprise fire-fighting facility production scheme data in real time; the data storage and management module is used for storing the data transmitted by the data acquisition and transmission module; the anomaly detection and processing module is used for carrying out feature recognition on the transmitted data feature vector by utilizing a data feature recognition technology; according to the invention, data preprocessing is carried out on the collected data by adopting a dynamic downsampling technology, so that the load and delay of data transmission can be reduced; the feature weights in the data model are subjected to iteration and replacement, so that the recognition accuracy of the data recognition model can be improved, the accuracy of abnormal detection and diagnosis of the enterprise fire-fighting facility production scheme is further improved, and normal production of fire-fighting facilities is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of data identification, and in particular to a remote diagnosis and analysis system for production plans of fire protection building engineering facilities. Background Art

[0002] During the production process of an enterprise, the production activities themselves will have a significant impact on the status of fire protection facilities. If the production scenario is not taken into consideration, false alarms or missed detections are likely to occur. By monitoring and analyzing various data in the production process of the enterprise, potential abnormalities can be identified and discovered so that timely measures can be taken to ensure the smooth progress of the production of fire protection facilities. In this way, abnormal detection and diagnosis of the production of enterprise fire protection facilities can be achieved.

[0003] Currently, anomaly detection and diagnosis of enterprise fire protection facility production plans faces the following challenges: During the process of collecting data related to the company's fire protection facility production plan, slow network transmission speed or insufficient data processing capacity resulted in the inability to monitor the status of production equipment in real time, delayed troubleshooting, and increased equipment maintenance costs; When controlling the quality of the enterprise's production process in the production plan, quality problems cannot be detected and diagnosed in a timely manner due to inaccurate inspection equipment or unreasonable setting of quality control points by staff, affecting production progress. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a remote diagnosis and analysis system for fire protection building engineering facility production solutions, including a data acquisition and transmission module, a data storage and management module, and an anomaly detection and processing module. The data acquisition and transmission module includes a data acquisition unit, a data processing unit and a data transmission unit, specifically: Real-time collection of production plan data of enterprise fire protection facilities, pre-processing of the collected data using dynamic downsampling technology, and data transmission of the pre-processed data through a combination of differential compression and dynamic Huffman coding technology; The data storage and management module includes a data receiving unit and a data storage unit, specifically: The CRC check code is used to verify and authenticate the transmitted data, thereby storing the authenticated data; The anomaly detection and processing module completes the quality inspection of the production plan by constructing a data recognition model, and uses historical data to train the data recognition model. At the same time, it optimizes the data recognition model by iteratively adjusting the feature weights, and then uses the loss function to evaluate the performance of the data recognition model. Finally, it completes the anomaly detection and diagnosis of the production plan based on the output results of the data recognition model.

[0006] As a preferred solution of the remote diagnosis and analysis system for the production plan of fire protection building engineering facilities described in the present invention, the data processing unit processes the data collected by the collection unit, specifically as follows: The data processing includes data arrangement and data preprocessing. The data arrangement is the temperature data collected. , production speed data and device status data Match with production equipment, then, ; Match the temperature data, production speed data and equipment status data with the corresponding production equipment according to the collection time to form three different data sets, and fuse the three sets into a new feature vector according to the set weight coefficient , and the fused feature vector For data processing, we have in, Respectively represent the weight coefficients of temperature data, production speed data and equipment status data, which are set according to the degree of influence of historical data on the production plan. It means that the temperature data, production speed data and equipment status data are sorted in time series, and the value of the equipment status data is 0 or 1. When the equipment status data is 0, it means that the current equipment is in good condition and operating normally. When the equipment status data is 1, it means that the current equipment is damaged. Represents a newly composed data set.

[0007] As a preferred solution of the remote diagnosis and analysis system for the production plan of fire protection building engineering facilities described in the present invention, the data preprocessing is to dynamically downsample the fused feature vector using dynamic downsampling technology, as follows: in, Indicates the downsampling interval, which is set by the implementer according to the specific implementation scenario and is not limited here. Indicates the production anomaly threshold, which is obtained by collecting historical data of production anomalies and averaging them. represents the feature vector after downsampling, represents the difference eigenvector.

[0008] As a preferred solution of the remote diagnosis and analysis system for the production plan of fire protection building engineering facilities described in the present invention, the data transmission unit is achieved by combining differential compression with dynamic Huffman coding, as follows: For the processed feature vector , select k data points before and after to form the transmission information , then there is, ; According to the constructed transmission information, the conditional distribution probability of the differential eigenvector is calculated, then, in, Indicates that information is being transmitted Next, the differential eigenvector The probability of represents the joint probability of the differential eigenvector and the transmitted information, represents the probability of transmitting information, Represents the transmission information of the composition; According to the calculated probability, the Huffman coding entropy is calculated as follows: in, represents the calculated Huffman coding entropy, Indicates that information is being transmitted Next, The difference eigenvector of the eigenvalues probability; Send the data with Huffman coding entropy to the data storage and management module.

[0009] As a preferred solution of the remote diagnosis and analysis system for the production plan of fire protection building engineering facilities described in the present invention, the data receiving unit verifies and authenticates the transmitted data through a built-in CRC check code, as follows: The CRC check code is calculated as follows: Using the calculated CRC check code for decoding, we have, in, Indicates built-in CRC check code, Indicates that information is being transmitted Next, The difference eigenvector of the eigenvalues The probability of represents the Huffman coding entropy in the transmitted data, Indicates the verification result of the transmitted data. According to the verification result, it is judged whether the current data transmission is complete. If so, When the comparison between the verification result and the data feature vector before transmission satisfies the formula When , it means the current data transmission is complete; When the comparison between the verification result and the data feature vector before transmission satisfies the formula , it means that the current data transmission is incomplete and data loss occurs. The data is retransmitted until the data is verified to be correct.

[0010] As a preferred solution of the remote diagnosis and analysis system for fire protection construction engineering facility production plan of the present invention, the method of training the data recognition model using historical data is as follows: Using historical data as a training dataset for the model , to mark normal samples and abnormal samples; Using the support vector machine algorithm to build a data recognition model, we have: in, Represents the model recognition result, represents the weight value, represents the bias term; Use the training data to train the constructed model to mark normal samples and abnormal samples, then we have, Initialize feature weight settings, ,and Indicates the first The initial weight of each feature; Perform weighted calculation on all feature vectors in the training set, then we have, in, Indicates the The weighted feature vector of the round iteration, represents the feature weight of the first iteration, Input all feature-weighted training sets into the model for training, then we have, in, Represents the classification results of all training sets, which are normal and abnormal states.

[0011] As a preferred solution of the remote diagnosis and analysis system for fire protection construction engineering facility production plan of the present invention, the optimization of the data recognition model by iteratively adjusting the feature weights is specifically as follows: By adjusting the feature weights, the output results of all training sets in the model are normal, then, The feature weights are adjusted iteratively, and the model output results after each feature weight adjustment are recorded. When the output results of the training set in the model are all normal, the iteration of the feature weights stops.

[0012] As a preferred solution of the remote diagnosis and analysis system for fire protection construction engineering facility production plan of the present invention, the performance evaluation of the data recognition model using the loss function is specifically as follows: Replace the initialized weights with the iterative weight features and use the loss function to evaluate the performance of the trained model. Then, in, represents the total number of features in the training set, Indicates the first The output of the model is The actual results of the characteristics of the current training set on the historical data are the actual impact of the currently selected characteristic values ​​on the production plan in the historical data. Represents the performance evaluation result of the model and satisfies the formula , it means the model performance evaluation has passed. Otherwise, the feature weights will be readjusted until the model performance evaluation has passed. Deploy the trained data recognition model to the production system to analyze and detect the data feature vectors collected during the production process in real time , and perform anomaly detection of the production plan based on the output results of the model, then, When the output result of the model is abnormal, the eigenvalue of the eigenvector of the current input model is located and analyzed, including the equipment number of the current eigenvalue, the production speed data of the current eigenvalue, and the equipment status of the current eigenvalue. Finally, based on the located data characteristics, relevant personnel are notified to perform maintenance to ensure the normal operation of the production plan.

[0013] The beneficial effects of the present invention are as follows: the present invention performs data preprocessing on the collected data by adopting dynamic downsampling technology, thereby ensuring dynamic downsampling of the fused feature vectors and reducing the load and delay of data transmission; the collected data is transmitted by combining differential compression with dynamic Huffman coding, thereby improving data compression efficiency on the basis of reducing the amount of data, thereby improving the data transmission quality; verifying the data through CRC coding can improve the accuracy of the data input into the data recognition model; by iteratively replacing the feature weights in the data recognition model, the recognition accuracy of the data recognition model can be improved, thereby improving the accuracy of abnormality detection and diagnosis of enterprise fire protection facilities, ensuring the normal production of fire protection facilities, and avoiding abnormalities. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them: Figure 1 This is a schematic diagram of the overall modules of a remote diagnosis and analysis system for a fire protection building engineering facility production solution of the present invention. DETAILED DESCRIPTION

[0015] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0017] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0018] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, these schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, three-dimensional dimensions, including length, width, and depth, should be included.

[0019] At the same time, in the description of the present invention, it should be noted that the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0020] In this disclosure, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0021] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a remote diagnosis and analysis system for production plans of fire protection building engineering facilities, including, a data acquisition and transmission module, a data storage and management module, and an anomaly detection and processing module; Specifically, the data collection and transmission module is used to collect the enterprise fire protection facility production plan data in real time, and transmit the collected data to the data storage and management module in real time. The data storage and management module is used to store the data transmitted by the data collection and transmission module through distributed storage technology, and manage the stored data using data access permission levels. By using data feature recognition technology to perform feature recognition on the transmitted data feature vectors, quality inspection and exception handling are performed on the enterprise fire protection facility production plan.

[0022] It should be noted that in the system composition mentioned in the present invention, the data acquisition and transmission module transmits the data collected in real time to the data storage and management module for storage and management; the data in the data storage and management module is accessed and analyzed in real time by the quality control and monitoring module for quality monitoring and early warning; after the anomaly detection and processing module detects an anomaly, it automatically generates a processing plan and optimization suggestions. The modules are closely linked to form a complete closed-loop system to ensure efficient operation from data acquisition, storage management, quality control to anomaly processing.

[0023] Furthermore, the data acquisition and transmission module is the basic module for abnormal detection and diagnosis of the enterprise fire protection facility production plan. It is responsible for real-time collection of various data in the production process and quickly and accurately transmits the collected data to the subsequent data storage and management module, including data acquisition unit, data processing unit and data transmission unit; the data acquisition unit uses wireless sensors to collect relevant data in the production process, including temperature data. , production speed data and device status data The data processing unit processes the data collected by the collection unit, and the data transmission unit transmits the data processed by the data processing unit to the data storage and management module using wireless transmission technology.

[0024] Specifically, data processing includes data arrangement and data preprocessing. Data arrangement is the collected temperature data. , production speed data and device status data Match with production equipment, then, , the collected data is matched one-to-one with the production equipment number to realize the abnormal location positioning of subsequent abnormality detection. Data preprocessing is to use dynamic downsampling technology to process the data collected by the acquisition unit to reduce the load and delay of data transmission. The details are as follows: Match the temperature data, production speed data and equipment status data with the corresponding production equipment according to the collection time to form three different data sets, and fuse the three sets into a new feature vector according to the set weight coefficient , and the fused feature vector For data processing, we have in, Respectively represent the weight coefficients of temperature data, production speed data and equipment status data, which are set according to the degree of influence of historical data on the production plan. It means that the temperature data, production speed data and equipment status data are sorted in time series, and the value of the equipment status data is 0 or 1. When the equipment status data is 0, it means that the current equipment is in good condition and operating normally. When the equipment status data is 1, it means that the current equipment is damaged. Represents a newly composed data set; Data preprocessing is to dynamically downsample the fused feature vector using dynamic downsampling technology, as follows: in, Indicates the downsampling interval, which is set by the implementer according to the specific implementation scenario and is not limited here. Indicates the production anomaly threshold, which is obtained by collecting historical data of production anomalies and averaging them. represents the feature vector after downsampling, represents the difference eigenvector.

[0025] Specifically, the data transmission unit combines differential compression with dynamic Huffman coding to improve data compression efficiency while reducing the amount of data, thereby improving data transmission quality. Specifically: For the processed feature vector , select k data points before and after to form the transmission information , then there is, ; According to the constructed transmission information, the conditional distribution probability of the differential eigenvector is calculated, then, in, Indicates that information is being transmitted Next, the differential eigenvector The probability of represents the joint probability of the differential eigenvector and the transmitted information, represents the probability of transmitting information, Represents the transmission information of the composition; According to the calculated probability, the Huffman coding entropy is calculated as follows: in, represents the calculated Huffman coding entropy, Indicates that information is being transmitted Next, The difference eigenvector of the eigenvalues probability; Send the data with Huffman coding entropy to the data storage and management module.

[0026] Furthermore, the data storage and management module transmits data by receiving the data acquisition and transmission module, and uses distributed storage technology to store the data, while setting the data access permission level to manage the stored data; The data storage and management module includes a data receiving unit, a data storage unit, and a data management unit. The data receiving unit verifies and authenticates the transmitted data through a built-in CRC check code, as follows: The CRC check code is calculated as follows:

[0027] Using the calculated CRC check code for decoding, we have,

[0028] in, Indicates built-in CRC check code, Indicates that information is being transmitted Next, The difference eigenvector of the eigenvalues The probability of represents the Huffman coding entropy in the transmitted data, Indicates the verification result of the transmitted data. According to the verification result, it is judged whether the current data transmission is complete. If so, When the comparison between the verification result and the data feature vector before transmission satisfies the formula When , it means the current data transmission is complete; When the comparison between the verification result and the data feature vector before transmission satisfies the formula , it means that the current data transmission is incomplete and data loss occurs. The data is retransmitted until the data is verified to be correct.

[0029] The data storage unit uses distributed storage technology to store the transmitted data on different storage nodes, as follows: By transforming the data feature vector Divide into multiple data slices; And adapt the consistent hashing algorithm to map the divided data slices to different storage nodes in real time. The consistent hashing algorithm is a well-known technology in this field and will not be described in detail in this embodiment. The implementer will select a specific application algorithm based on the actual application scenario. At the same time, corresponding check codes are generated for the divided data slices to ensure the integrity of the data during storage.

[0030] Furthermore, the anomaly detection and processing module performs quality inspection and anomaly processing on the production plan by using data feature recognition technology to perform feature recognition on the transmitted data feature vector; Data feature recognition technology is to build a data recognition model and transform the data feature vector As the input of the model, the quality inspection of the production plan is realized according to the output of the model, as follows: For the feature vector , based on the characteristic factors affecting quality inspection, including temperature fluctuations, production speed changes and equipment status indicators, new eigenvalues ​​are selected to form a eigenvector Represents data features extracted from temperature data, production speed data, and equipment status data; Using historical data as a training dataset for the model , to mark normal samples and abnormal samples; Using the support vector machine algorithm to build a data recognition model, we have: in, Represents the model recognition result, represents the weight value, Indicates the bias term. The weight value and the value of the bias term are set by the implementer according to the specific implementation scenario and are not limited here. Use the training data to train the constructed model to mark normal samples and abnormal samples, then we have, Initialize feature weight settings, ,and Indicates the first The initial weight of each feature; Perform weighted calculation on all feature vectors in the training set, then we have, in, Indicates the The weighted feature vector of the round iteration, Indicates the The feature weights of the round iteration, Input all feature-weighted training sets into the model for training, then we have, in, Represents the classification results of all training sets, which are normal and abnormal. By adjusting the feature weights, the output results of all training sets in the model are normal, then,

[0031] in, Indicates the The feature weights of the round iteration, Indicates the The feature weights of the round iteration, Indicates the change in feature weight; Iteratively adjust the feature weights and record the model output results after each feature weight adjustment. When the output results of the training set in the model are all normal, the iteration of the feature weights stops. Replace the initialized weights with the iterative weight features and use the loss function to evaluate the performance of the trained model. Then, in, represents the total number of features in the training set, Indicates the first The output of the model is The actual results of the characteristics of the current training set on the historical data are the actual impact of the currently selected characteristic values ​​on the production plan in the historical data. Represents the performance evaluation result of the model and satisfies the formula , it means the model performance evaluation has passed. Otherwise, the feature weights will be readjusted until the model performance evaluation has passed. Deploy the trained data recognition model to the production system to analyze and detect the data feature vectors collected during the production process in real time , and perform anomaly detection of the production plan based on the output results of the model, then, When the output result of the model is abnormal, the eigenvalue of the eigenvector of the current input model is located and analyzed, including the equipment number of the current eigenvalue, the production speed data of the current eigenvalue, and the equipment status of the current eigenvalue. Finally, based on the located data characteristics, relevant personnel are notified to perform maintenance to ensure the normal operation of the fire protection facility production plan, ensure the normal production of fire protection facilities, and avoid abnormalities.

[0032] Furthermore, if the function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0033] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0034] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0035] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention).

[0036] It should be understood that in the development of any actual embodiment, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, the development effort will be a routine task of design, fabrication, and production without undue experimentation.

[0037] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A remote diagnosis and analysis system for production plans of fire protection construction engineering facilities, characterized by: Including data acquisition and transmission module, data storage and management module and anomaly detection and processing module, The data acquisition and transmission module includes a data acquisition unit, a data processing unit and a data transmission unit, specifically: Real-time collection of production plan data of enterprise fire protection facilities, pre-processing of the collected data using dynamic downsampling technology, and data transmission of the pre-processed data through a combination of differential compression and dynamic Huffman coding technology; The data storage and management module includes a data receiving unit and a data storage unit, specifically: The CRC check code is used to verify and authenticate the transmitted data, thereby storing the authenticated data; The anomaly detection and processing module completes the quality inspection of the production plan by constructing a data recognition model, and uses historical data to train the data recognition model. At the same time, it optimizes the data recognition model by iteratively adjusting the feature weights, and then uses the loss function to evaluate the performance of the data recognition model. Finally, it completes the anomaly detection of the production plan based on the output results of the data recognition model.

2. A remote diagnosis and analysis system for production plans of fire protection construction engineering facilities according to claim 1, characterized in that: The data processing unit processes the data collected by the collection unit, specifically as follows: The data processing includes data arrangement and data preprocessing. The data arrangement is the temperature data collected. , production speed data and device status data Match with production equipment, then, ; Match the temperature data, production speed data and equipment status data with the corresponding production equipment according to the collection time to form three different data sets, and fuse the three sets into a new feature vector according to the set weight coefficient , and the fused feature vector For data processing, we have in, Respectively represent the weight coefficients of temperature data, production speed data and equipment status data, which are set according to the degree of influence of historical data on the production plan. It means that the temperature data, production speed data and equipment status data are sorted in time series, and the value of the equipment status data is 0 or 1. When the equipment status data is 0, it means that the current equipment is in good condition and operating normally. When the equipment status data is 1, it means that the current equipment is damaged. Represents a newly composed data set.

3. A remote diagnosis and analysis system for fire protection construction engineering facility production plans according to claim 2, characterized in that: The data preprocessing is to dynamically downsample the fused feature vectors using dynamic downsampling technology, as follows: in, Indicates the downsampling interval, which is set by the implementer according to the specific implementation scenario and is not limited here. Indicates the production anomaly threshold, which is obtained by collecting historical data of production anomalies and averaging them. represents the feature vector after downsampling, represents the difference eigenvector.

4. A remote diagnosis and analysis system for production plans of fire protection construction engineering facilities according to claim 3, characterized in that: The data transmission unit is achieved by combining differential compression with dynamic Huffman coding, as follows: For the processed feature vector , select k data points before and after to form the transmission information , then there is, ; According to the constructed transmission information, the conditional distribution probability of the differential eigenvector is calculated, then, in, Indicates that information is being transmitted Next, the differential eigenvector The probability of represents the joint probability of the differential eigenvector and the transmitted information, represents the probability of transmitting information, Represents the transmission information of the composition; According to the calculated probability, the Huffman coding entropy is calculated as follows: in, represents the calculated Huffman coding entropy, Indicates that information is being transmitted Next, The difference eigenvector of the eigenvalues probability; Send the data with Huffman coding entropy to the data storage and management module.

5. A remote diagnosis and analysis system for production plans of fire protection construction engineering facilities according to claim 4, characterized in that: The data receiving unit verifies and authenticates the transmitted data using a built-in CRC check code, as follows: The CRC check code is calculated as follows: Using the calculated CRC check code for decoding, we have, in, Indicates built-in CRC check code, Indicates that information is being transmitted Next, The difference eigenvector of the eigenvalues The probability of represents the Huffman coding entropy in the transmitted data, Indicates the verification result of the transmitted data. According to the verification result, it is judged whether the current data transmission is complete. If so, When the comparison between the verification result and the data feature vector before transmission satisfies the formula When , it means the current data transmission is complete; When the comparison between the verification result and the data feature vector before transmission satisfies the formula , it means that the current data transmission is incomplete and data loss occurs. The data is retransmitted until the data is verified to be correct.

6. A remote diagnosis and analysis system for production plans of fire protection construction engineering facilities according to claim 5, characterized in that: The specific method of training the data recognition model using historical data is as follows: Using historical data as a training dataset for the model , to mark normal samples and abnormal samples; Using the support vector machine algorithm to build a data recognition model, we have: in, Represents the model recognition result, represents the weight value, represents the bias term; Use the training data to train the constructed model to mark normal samples and abnormal samples, then we have, Initialize feature weight settings, ,and Indicates the first The initial weight of each feature; Perform weighted calculation on all feature vectors in the training set, then we have, in, Indicates the The weighted feature vector of the round iteration, represents the feature weight of the first iteration, Input all feature-weighted training sets into the model for training, then we have, in, Represents the classification results of all training sets, which are normal and abnormal states.

7. A remote diagnosis and analysis system for production plans of fire protection construction engineering facilities according to claim 6, characterized in that: The optimization of the data recognition model by iteratively adjusting the feature weights is specifically as follows: By adjusting the feature weights, the output results of all training sets in the model are normal, then, The feature weights are adjusted iteratively, and the model output results after each feature weight adjustment are recorded. When the output results of the training set in the model are all normal, the iteration of the feature weights stops.

8. A remote diagnosis and analysis system for production plans of fire protection construction engineering facilities according to claim 7, characterized in that: The performance evaluation of the data recognition model using the loss function is specifically as follows: Replace the initialized weights with the iterative weight features and use the loss function to evaluate the performance of the trained model. Then, in, represents the total number of features in the training set, Indicates the first The output of the model is The actual results of the characteristics of the current training set on the historical data are the actual impact of the currently selected characteristic values ​​on the production plan in the historical data. Represents the performance evaluation result of the model and satisfies the formula , it means the model performance evaluation has passed. Otherwise, the feature weights will be readjusted until the model performance evaluation has passed. Deploy the trained data recognition model to the production system to analyze and detect the data feature vectors collected during the production process in real time , and perform anomaly detection of the production plan based on the output results of the model, then, When the output result of the model is abnormal, the eigenvalue of the eigenvector of the current input model is located and analyzed, including the equipment number of the current eigenvalue, the production speed data of the current eigenvalue, and the equipment status of the current eigenvalue. Finally, based on the located data characteristics, relevant personnel are notified to perform maintenance to ensure the normal operation of the production plan.

Images