A safety monitoring platform for marine boilers

Abstract

The present invention belongs to the technical field of safety monitoring of marine boilers. The present invention discloses a safety monitoring platform for marine boilers. The method comprises: setting a safety monitoring device for marine boilers, collecting boiler status characteristic data, the boiler status characteristic data comprising working status data and standard working status data in the boiler, the working status data comprising real-time working status data, preset flue gas emission and preset water hardness; evaluating whether the boiler is operating through the real-time working status data, and generating a working safety assessment coefficient; comparing and analyzing the working safety assessment coefficient with a preset working safety assessment coefficient threshold, and determining whether to generate an early warning message; if the early warning message is generated, inputting the flue gas emission characteristic data and the standard flue gas emission characteristic data into a pre-constructed boiler flue gas emission prediction model, obtaining the predicted flue gas emission, and determining whether to generate an operation stop instruction, thereby improving the safety of the use of marine boilers.

Description

Technical Field

[0001] The invention belongs to the technical field of marine boilers, and in particular relates to a safety monitoring platform for marine boilers. Background Art

[0002] As one of the important power units of a ship, a marine boiler is responsible for providing steam power to drive the operation of the ship. In order to ensure the safe and efficient operation of marine boilers, an effective safety monitoring system must be equipped to monitor key parameters in a timely manner and take corresponding measures to avoid accidents.

[0003] The existing Chinese patent application with publication number CN110986378A discloses a boiler safety monitoring platform. The invention relates to a monitoring platform, specifically to a boiler safety monitoring platform, including: a data acquisition and communication module, used to collect data information on boiler inlet temperature, inlet pressure, outlet temperature, water storage pressure and gas leakage; a data transmission module, used to transmit the data information collected by the data acquisition and communication module; a remote monitoring terminal, used to receive data transmitted by the data transmission module, and display the received data information in real time; solve the problem of low efficiency and untimely inspection of boilers caused by traditional manual inspection methods for boiler safety inspections.

[0004] The existing Chinese patent with publication number CN106568076B discloses a boiler protection control system, including a temperature detector, a liquid level detector and a pressure detector connected to the input end of the controller, an automatic regulating valve and a vent valve connected to the output end of the controller; and also includes a safety regulating valve arranged on the boiler drum, the safety regulating valve including a valve body with a valve cover, a valve port is opened at the bottom of the valve body, a steam exhaust port is opened on the side wall, a valve stem is arranged in the inner cavity of the valve body, a valve core abutting against the valve port is arranged at the bottom of the valve stem, a spring is sleeved on the valve stem and a spring limit buckle is arranged, the spring is limited between the spring limit buckle and the valve core, and a limit rod passes through the side wall of the valve body and the upper end of the valve stem in the horizontal direction. The invention has the advantages of perfect safety monitoring means; simple structure of the safety valve and convenient assembly and disassembly.

[0005] However, the above prior art still has the following problems:

[0006] Boilers are important equipment in industrial production. Safety monitoring and control systems must be highly stable and reliable to ensure continuous safe operation. However, the accuracy and timeliness of data may be affected by environmental interference factors. For example, unqualified boiler water quality or large fluctuations in water quality may cause scaling, corrosion and other problems, affecting the safe operation of the boiler. Poor smoke exhaust can also cause smoke to accumulate in the combustion chamber and even flow back into the boiler room, increasing the risk of explosion and fire. Therefore, ensuring the accuracy and timeliness of data is crucial for effective monitoring of the system. Summary of the invention

[0007] The purpose of the present invention is to provide a safety monitoring platform for marine boilers, which evaluates whether the boiler is in operation through real-time working status data and generates a working safety assessment coefficient; compares and analyzes the working safety assessment coefficient with a preset working safety assessment coefficient threshold to determine whether to generate an early warning message; if an early warning message is generated, the flue gas emission characteristic data and the standard flue gas emission characteristic data are input into a pre-built boiler flue gas emission prediction model to obtain the predicted flue gas emission amount, and determine whether to generate a stop operation instruction, thereby solving the problems that the accuracy and timeliness of existing data may be affected by environmental interference factors and the safe operation of the boiler.

[0008] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0009] The present invention is a safety monitoring platform for marine boilers, comprising.

[0010] A safety monitoring device for a marine boiler is provided, comprising a control system, a temperature sensor arranged on the left outer wall of a furnace, a safety valve arranged on the upper left of a boiler shell, a pressure sensor on the safety valve, a flue gas emission probe on the upper right of the boiler shell, and a water quality regulating device arranged on a water inlet pipe on the right outer wall of the furnace, wherein the temperature sensor, the pressure sensor, the flue gas emission probe and the water quality regulating device are connected by wire and / or wirelessly to achieve mutual transmission of data;

[0011] Collect boiler status characteristic data, the boiler status characteristic data includes working status data and standard working status data in the boiler, the working status data includes real-time working status data, preset flue gas emission and preset water hardness;

[0012] Evaluate whether the boiler is operating through real-time working status data and generate a working safety assessment coefficient;

[0013] Compare and analyze the work safety assessment coefficient with the preset work safety assessment coefficient threshold to determine whether to generate early warning information;

[0014] If warning information is generated, the flue gas emission characteristic data and the standard flue gas emission characteristic data are input into a pre-built boiler flue gas emission prediction model to obtain the predicted flue gas emission;

[0015] Determine whether to generate a stop operation instruction according to the predicted smoke emission;

[0016] According to the stop operation instruction, suspend the operation of the boiler;

[0017] Furthermore, the real-time working status data includes furnace temperature, furnace pressure, flue gas emission and water hardness; the standard working status data includes standard furnace temperature, standard furnace pressure, standard flue gas emission and standard water hardness;

[0018] Evaluate whether the boiler is operating through real-time working status data and generate a working safety assessment coefficient;

[0019]

[0020] In the formula, is the work safety assessment factor, is the flue gas emission, is the furnace temperature, is the furnace pressure, is the water hardness; , , , The values ​​are all greater than 0. is the weight factor of flue gas emissions, is the weight factor of furnace temperature, is the weight factor of furnace pressure, is the weighting factor of water hardness.

[0021] Furthermore, the method of whether to generate warning information includes:

[0022] If the work safety assessment coefficient is less than or equal to the preset work safety assessment coefficient threshold, a warning message is generated;

[0023] If the work safety assessment coefficient is greater than the preset work safety assessment coefficient threshold, no warning information is generated;

[0024] Furthermore, the method for pre-constructing the boiler flue gas emission prediction model includes:

[0025] Pre-collect j groups of flue gas emission training data, where j is an integer greater than 1, and the flue gas emission training data includes flue gas emission characteristic data and predicted flue gas emission corresponding to the flue gas emission characteristic data; the flue gas emission training data includes the flue gas emission of the boiler and the preset flue gas emission; the flue gas emission is the flue gas emission measured by the flue gas emission probe arranged on the upper right of the boiler shell;

[0026] Divide the flue gas emission training data into a training set and a test set, build a classifier, use the flue gas emission characteristic data in the training set as input data, use the flue gas emission amount in the training set as output data, train the classifier to obtain an initial classifier, use the test set to test the initial classifier, and output a classifier that meets the preset accuracy as a boiler flue gas emission prediction model, the boiler flue gas emission prediction model is one of the models such as naive Bayes algorithm, random forest regression or neural network regression;

[0027] Furthermore, the method for determining whether to generate a stop operation instruction includes:

[0028] If the predicted smoke emission is less than the preset smoke emission threshold, a stop operation instruction is generated;

[0029] If the predicted smoke emission is greater than or equal to the preset smoke emission threshold, a stop operation instruction is generated;

[0030] Furthermore, the boiler flue gas emission prediction model also includes a boiler water hardness prediction model; the water hardness characteristic data and the standard water hardness characteristic data are input into the pre-constructed boiler water hardness prediction model to obtain the predicted water hardness;

[0031] Furthermore, the method for pre-constructing the boiler water hardness prediction model includes:

[0032] Pre-collect q groups of water hardness training data, where q is an integer greater than 1, and the water hardness training data includes water hardness characteristic data and water hardness corresponding to the water hardness characteristic data; the water hardness characteristic data includes the water hardness of the boiler and the preset water hardness, and the water hardness is the water hardness measured by the water quality regulating device arranged on the water inlet pipe on the right outer wall of the furnace;

[0033] The water hardness training data is divided into a training set and a test set, and a classifier is constructed. The water hardness feature data in the training set is used as input data, and the water hardness in the training set is used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set. The classifier that meets the preset accuracy is output as a boiler water hardness prediction model. The boiler water hardness prediction model is one of the models such as the naive Bayes algorithm, random forest regression or neural network regression.

[0034] Further, according to the predicted water hardness, the method for determining whether to generate a stop operation instruction includes:

[0035] If the predicted water hardness is greater than or equal to the preset water hardness threshold, a stop operation instruction is generated;

[0036] If the predicted water hardness is less than the preset water hardness threshold, no stop operation instruction is generated;

[0037] A safety monitoring system for a marine boiler, used to implement the safety monitoring platform for a marine boiler, comprising:

[0038] The device setting module includes a control system, a temperature sensor arranged on the left outer wall of the furnace, a safety valve arranged on the upper left of the boiler shell, a pressure sensor on the safety valve, a flue gas emission probe on the upper right of the boiler shell, and a water quality regulating device arranged on the water inlet pipe on the right outer wall of the furnace, wherein the temperature sensor, the pressure sensor, the flue gas emission probe and the water quality regulating device are connected by wire and / or wirelessly to realize mutual transmission of data;

[0039] A data acquisition module is used to collect boiler status characteristic data, the boiler status characteristic data includes working status data and standard working status data in the boiler, the working status data includes real-time working status data, preset flue gas emission and preset water hardness;

[0040] The boiler working status information prediction module evaluates whether the boiler is operating through real-time working status data and generates a working safety assessment coefficient;

[0041] The safety warning module compares and analyzes the work safety assessment coefficient with the preset work safety assessment coefficient threshold to determine whether to generate a warning message;

[0042] The decision module, if warning information is generated, inputs the flue gas emission characteristic data and the standard flue gas emission characteristic data into a pre-built boiler flue gas emission prediction model to obtain the predicted flue gas emission;

[0043] According to the predicted flue gas emission, it is determined whether to generate a stop operation instruction; according to the stop operation instruction, the operation of the boiler is suspended.

[0044] The present invention has the following beneficial effects:

[0045] 1. The present invention can improve the operating efficiency of the equipment: by setting up a safety monitoring device for marine boilers, the operating status of the equipment can be monitored in real time, potential failures can be predicted, and an optimized maintenance plan can be formulated, which can reduce maintenance costs, improve equipment utilization, and avoid production stagnation and increased maintenance costs caused by equipment failures.

[0046] 2. The present invention takes into account that the accuracy and timeliness of data may be affected by environmental interference factors, solves the problems of scaling and corrosion caused by unqualified boiler water quality or large fluctuations in water quality, and ensures the safe operation of the boiler; at the same time, it takes into account that poor smoke exhaust may also cause smoke to accumulate in the combustion chamber and even flow back into the boiler room, increasing the risk of explosion and fire; through early warning information and predictive machine learning models, potential problems of equipment can be discovered in time, which can reduce the possibility of accidents and improve the safety of marine boiler use.

[0047] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0049] Figure 1 The figure is a schematic diagram of the structure of a safety monitoring device for a marine boiler.

[0050] Figure 2 The figure is a module diagram of a safety monitoring platform for marine boilers.

[0051] Figure 3 The present invention is a flow chart of a method for safety monitoring of a marine boiler.

[0052] Figure 4 is a schematic diagram of an electronic device of the present invention;

[0053] Figure 5 It is a schematic diagram of the storage medium of the present invention;

[0054] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0055] 1-furnace, 2-temperature sensor, 3-boiler shell, 4-safety valve, 5-pressure sensor, 6-flue gas emission probe, 7-water quality regulating device. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Specific embodiment 1

[0058] See also Figure 1 As shown, the safety monitoring platform for marine boilers described in this embodiment includes a device setting module, a data acquisition module, a boiler working status information prediction module, a safety warning module and a decision-making module; the above modules are connected by wire and / or wirelessly to achieve mutual transmission of data;

[0059] The device setting module is provided with a safety monitoring device for a marine boiler, including a control system, a temperature sensor 2 arranged on the left outer wall of a furnace 1, a safety valve 4 arranged on the upper left of a boiler shell 3, a pressure sensor 5 on the safety valve 4, a flue gas emission probe 6 on the upper right of the boiler shell 3, and a water quality regulating device 7 arranged on the water inlet pipe on the right outer wall of the furnace 1, wherein the temperature sensor 2, the pressure sensor 5, the flue gas emission probe 6 and the water quality regulating device 7 are connected by wire and / or wirelessly to realize mutual transmission of data;

[0060] A data acquisition module collects boiler status characteristic data, the boiler status characteristic data includes working status data and standard working status data in the boiler, the working status data includes real-time working status data, preset flue gas emission and preset water hardness;

[0061] The real-time working status data includes furnace temperature, furnace pressure, flue gas emission and water hardness; the standard working status data includes standard furnace temperature, standard furnace pressure, standard flue gas emission and standard water hardness;

[0062] The methods for obtaining the furnace temperature include:

[0063] The boiler staff obtains the data through the temperature sensor and uploads it to the system;

[0064] Methods for obtaining furnace pressure include:

[0065] The boiler staff obtains the data through the pressure sensor and uploads it to the system;

[0066] Methods for obtaining flue gas emissions include:

[0067] The data is obtained by boiler staff through flue gas emission probes and uploaded to the system;

[0068] Methods for obtaining water hardness include:

[0069] The boiler staff obtains the water quality through the water quality regulating valve and uploads it to the system;

[0070] The boiler working status information prediction module evaluates whether the boiler is operating through real-time working status data and generates a working safety assessment coefficient;

[0071]

[0072] In the formula, is the work safety assessment factor, is the flue gas emission, is the furnace temperature, is the furnace pressure, is the water hardness; , , , The values ​​are all greater than 0. is the weight factor of flue gas emissions, is the weight factor of furnace temperature, is the weight factor of furnace pressure, is the weighting factor of water hardness.

[0073] The safety warning module compares and analyzes the work safety assessment coefficient with the preset work safety assessment coefficient threshold to determine whether to generate a warning message;

[0074] The method of whether to generate early warning information includes:

[0075] If the work safety assessment coefficient is less than or equal to the preset work safety assessment coefficient threshold, a warning message is generated;

[0076] If the work safety assessment coefficient is greater than the preset work safety assessment coefficient threshold, no warning information is generated;

[0077] The decision module, if warning information is generated, inputs the flue gas emission characteristic data and the standard flue gas emission characteristic data into a pre-built boiler flue gas emission prediction model to obtain the predicted flue gas emission;

[0078] Determine whether to generate a stop operation instruction according to the predicted smoke emission;

[0079] According to the stop operation instruction, suspend the operation of the boiler;

[0080] The real-time working status data includes furnace temperature, furnace pressure, flue gas emission and water hardness; the standard working status data includes standard furnace temperature, standard furnace pressure, standard flue gas emission and standard water hardness;

[0081] The method for pre-constructing the boiler flue gas emission prediction model comprises:

[0082] Pre-collect j groups of flue gas emission training data, where j is an integer greater than 1, and the flue gas emission training data includes flue gas emission characteristic data and predicted flue gas emission corresponding to the flue gas emission characteristic data; the flue gas emission training data includes the flue gas emission of the boiler and the preset flue gas emission; the flue gas emission is the flue gas emission measured by the flue gas emission probe arranged on the upper right of the boiler shell;

[0083] Divide the flue gas emission training data into a training set and a test set, build a classifier, use the flue gas emission characteristic data in the training set as input data, use the flue gas emission amount in the training set as output data, train the classifier to obtain an initial classifier, use the test set to test the initial classifier, and output a classifier that meets the preset accuracy as a boiler flue gas emission prediction model, the boiler flue gas emission prediction model is one of the models such as naive Bayes algorithm, random forest regression or neural network regression;

[0084] The method for determining whether to generate a stop operation instruction comprises:

[0085] If the predicted smoke emission is less than the preset smoke emission threshold, a stop operation instruction is generated;

[0086] If the predicted smoke emission is greater than or equal to the preset smoke emission threshold, a stop operation instruction is generated;

[0087] In this embodiment, a safety monitoring platform for a marine boiler is based on a safety monitoring device for a marine boiler. The boiler state characteristic data is collected by setting a safety monitoring device for the marine boiler in advance. The boiler state characteristic data includes working state data and standard working state data in the boiler. The working state data includes real-time working state data, preset flue gas emission and preset water hardness. Whether the boiler is operating is evaluated by real-time working state data, and a working safety assessment coefficient is generated. The working safety assessment coefficient is compared and analyzed with a preset working safety assessment coefficient threshold to determine whether to generate an early warning message. If an early warning message is generated, the flue gas emission characteristic data and the standard flue gas emission characteristic data are input into a pre-built boiler flue gas emission prediction model to obtain a predicted flue gas emission. According to the predicted flue gas emission, it is determined whether to generate a stop operation instruction.

[0088] Taking into account the possibility that the accuracy and timeliness of the data may be affected by environmental interference factors, the problem of scaling and corrosion caused by unqualified boiler water quality or large fluctuations in water quality is solved, ensuring the safe operation of the boiler. At the same time, it is considered that poor smoke exhaust will also cause smoke to accumulate in the combustion chamber and even flow back into the boiler room, increasing the risk of explosion and fire. Through early warning information and predictive machine learning models, potential equipment problems can be discovered in a timely manner, which can reduce the possibility of accidents and improve the safety of marine boiler use. Specific embodiment 2

[0090] This embodiment further improves the design on the basis of the first embodiment. The difference is that this embodiment provides a safety monitoring of a marine boiler, wherein the boiler flue gas emission prediction model also includes a boiler water hardness prediction model; the water hardness characteristic data and the standard water hardness characteristic data are input into the pre-constructed boiler water hardness prediction model to obtain the predicted water hardness;

[0091] The method for pre-constructing the boiler water hardness prediction model includes:

[0092] Pre-collect q groups of water hardness training data, where q is an integer greater than 1, and the water hardness training data includes water hardness characteristic data and water hardness corresponding to the water hardness characteristic data; the water hardness characteristic data includes the water hardness of the boiler and the preset water hardness, and the water hardness is the water hardness measured by the water quality regulating device arranged on the water inlet pipe on the right outer wall of the furnace;

[0093] The water hardness training data is divided into a training set and a test set, and a classifier is constructed. The water hardness feature data in the training set is used as input data, and the water hardness in the training set is used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set. The classifier that meets the preset accuracy is output as a boiler water hardness prediction model. The boiler water hardness prediction model is one of the models such as the naive Bayes algorithm, random forest regression or neural network regression.

[0094] The method for determining whether to generate a stop operation instruction based on the predicted water hardness includes:

[0095] If the predicted water hardness is greater than or equal to the preset water hardness threshold, a stop operation instruction is generated;

[0096] If the predicted water hardness is less than the preset water hardness threshold, no stop operation instruction is generated. Specific embodiment three

[0098] See also Figure 3 As shown, the part not described in detail in this embodiment is described in the first embodiment, which provides a safety monitoring method for a marine boiler, comprising:

[0099] A safety monitoring device for a marine boiler is provided, comprising a control system, a temperature sensor (2) arranged on the left outer wall of a furnace (1), a safety valve (4) arranged on the upper left of a boiler shell (3), a pressure sensor (5) on the safety valve (4), a flue gas emission probe (6) on the upper right of the boiler shell (3), and a water quality regulating device (7) arranged on a water inlet pipe on the right outer wall of the furnace (1), wherein the temperature sensor (2), the pressure sensor (5), the flue gas emission probe (6) and the water quality regulating device (7) are connected by wire and / or wirelessly to achieve mutual transmission of data;

[0100] Collect boiler status characteristic data, the boiler status characteristic data includes working status data and standard working status data in the boiler, the working status data includes real-time working status data, preset flue gas emission and preset water hardness;

[0101] Evaluate whether the boiler is operating through real-time working status data and generate a working safety assessment coefficient;

[0102] Compare and analyze the work safety assessment coefficient with the preset work safety assessment coefficient threshold to determine whether to generate early warning information;

[0103] If warning information is generated, the flue gas emission characteristic data and the standard flue gas emission characteristic data are input into a pre-built boiler flue gas emission prediction model to obtain the predicted flue gas emission;

[0104] According to the predicted flue gas emission, it is determined whether to generate a stop operation instruction; according to the stop operation instruction, the operation of the boiler is suspended. Specific embodiment 4

[0106] See also Figure 4 As shown, according to another aspect of the present application, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, the dynamic path adjustment method for the wafer handling robot arm as described above may be executed.

[0107] The method or system according to the embodiment of the present application can also be used by Figure 4 The electronic device architecture shown in FIG. Figure 4 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, an input / output 506, a hard disk 507, etc. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store a safety monitoring platform for marine boilers provided in the present application. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of an electronic device are shown. Specific embodiment five

[0109] See also Figure 5 As shown, a computer-readable storage medium 250 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 250. When the computer-readable instructions are executed by the processor, a safety monitoring method for a marine boiler according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 250 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0110] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0111] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A safety monitoring platform for marine boilers, characterized in that: The monitoring method of the security monitoring platform specifically includes the following steps: A set of security monitoring devices is set up to achieve mutual transmission of data through wired and / or wireless connections; Collect boiler status characteristic data, the boiler status characteristic data includes working status data and standard working status data in the boiler, the working status data includes real-time working status data, preset flue gas emission and preset water hardness; Evaluate whether the boiler is operating through real-time working status data and generate a working safety assessment coefficient; Compare and analyze the work safety assessment coefficient with the preset work safety assessment coefficient threshold to determine whether to generate early warning information; If warning information is generated, the flue gas emission characteristic data and the standard flue gas emission characteristic data are input into a pre-built boiler flue gas emission prediction model to obtain the predicted flue gas emission; Determine whether to generate a stop operation instruction according to the predicted smoke emission; According to the stop operation instruction, the boiler operation is suspended.

2. A safety monitoring platform for marine boilers according to claim 1, characterized in that: The real-time working status data includes furnace temperature, furnace pressure, flue gas emission and water hardness; the standard working status data includes standard furnace temperature, standard furnace pressure, standard flue gas emission and standard water hardness.

3. A safety monitoring platform for marine boilers according to claim 1, characterized in that: The real-time working status data is used to evaluate whether the boiler is operating and generate a working safety assessment coefficient, which is calculated using the following formula; ； In the formula, is the work safety assessment factor, is the flue gas emission, is the furnace temperature, is the furnace pressure, is the water hardness; , , , The values ​​are all greater than 0. is the weight factor of flue gas emissions, is the weight factor of furnace temperature, is the weight factor of furnace pressure, is the weighting factor of water hardness.

4. A safety monitoring platform for marine boilers according to claim 1, characterized in that: The method of whether to generate warning information includes: If the work safety assessment coefficient is less than or equal to the preset work safety assessment coefficient threshold, a warning message is generated; If the work safety assessment coefficient is greater than the preset work safety assessment coefficient threshold, no warning information is generated.

5. A safety monitoring platform for marine boilers according to claim 1, characterized in that: The method for pre-constructing the boiler flue gas emission prediction model comprises: Pre-collect j groups of flue gas emission training data, where j is an integer greater than 1, and the flue gas emission training data includes flue gas emission characteristic data and predicted flue gas emission corresponding to the flue gas emission characteristic data; the flue gas emission training data includes the flue gas emission of the boiler and the preset flue gas emission; the flue gas emission is the flue gas emission measured by the flue gas emission probe arranged on the upper right of the boiler shell; The flue gas emission training data is divided into a training set and a test set, and a classifier is constructed. The flue gas emission characteristic data in the training set is used as input data, and the flue gas emission amount in the training set is used as output data. The classifier is trained to obtain an initial classifier, and the initial classifier is tested using the test set. The classifier that meets the preset accuracy is output as a boiler flue gas emission prediction model. The boiler flue gas emission prediction model is one of the naive Bayes algorithm, random forest regression or neural network regression model.

6. A safety monitoring platform for marine boilers according to claim 1, characterized in that: The safety monitoring device comprises a control system, a temperature sensor (2) arranged on the left outer wall of a furnace (1), a safety valve (4) arranged on the upper left of a boiler shell (3), a pressure sensor (5) on the safety valve (4), a flue gas emission probe (6) on the upper right of the boiler shell (3), and a water quality regulating device (7) arranged on a water inlet pipe on the right outer wall of the furnace (1). The temperature sensor (2), the pressure sensor (5), the flue gas emission probe (6) and the water quality regulating device (7) are connected by wire and / or wirelessly to achieve mutual transmission of data.

7. A safety monitoring system for a marine boiler, used to implement a safety monitoring platform for a marine boiler as claimed in any one of claims 1 to 6, characterized in that: include: A data acquisition module is used to collect boiler status characteristic data, the boiler status characteristic data includes working status data and standard working status data in the boiler, the working status data includes real-time working status data, preset flue gas emission and preset water hardness; The boiler working status information prediction module evaluates whether the boiler is operating through real-time working status data and generates a working safety assessment coefficient; The safety warning module compares and analyzes the work safety assessment coefficient with the preset work safety assessment coefficient threshold to determine whether to generate a warning message; The decision module, if warning information is generated, inputs the flue gas emission characteristic data and the standard flue gas emission characteristic data into the pre-built boiler flue gas emission prediction model to obtain the predicted flue gas emission.

Images